Doberman-Core good first issues (Python)

chore: adopt changelog fragments so PRs stop colliding on CHANGELOG.md 2 months ago

enhancement good first issue level-3

111

Doberman is an AI agent security framework for guardrails, prompt injection defense, runtime policy enforcement, tool-use permissions, agent monitoring, audit logs, LLM safety, autonomous workflow protection and secure AI deployment.

Python

cli: add `--json` to `doberman memory` 2 months ago

enhancement good first issue level-3

fu351/Doberman-Core

111

Doberman is an AI agent security framework for guardrails, prompt injection defense, runtime policy enforcement, tool-use permissions, agent monitoring, audit logs, LLM safety, autonomous workflow protection and secure AI deployment.

Python

storage: `--last 0` returns every row instead of none 2 months ago

bug good first issue level-3

fu351/Doberman-Core

111

Doberman is an AI agent security framework for guardrails, prompt injection defense, runtime policy enforcement, tool-use permissions, agent monitoring, audit logs, LLM safety, autonomous workflow protection and secure AI deployment.

Python

cli: add `--quiet` to `doberman demo` so it can run as a CI smoke test 2 months ago

enhancement good first issue level-3

fu351/Doberman-Core

111

Doberman is an AI agent security framework for guardrails, prompt injection defense, runtime policy enforcement, tool-use permissions, agent monitoring, audit logs, LLM safety, autonomous workflow protection and secure AI deployment.

Python

calibrate_perplexity_threshold: the model-agnostic half of the perplexity seam (OT.3) 2 months ago

enhancement help wanted good first issue roadmap level-4

fu351/Doberman-Core

111

Doberman is an AI agent security framework for guardrails, prompt injection defense, runtime policy enforcement, tool-use permissions, agent monitoring, audit logs, LLM safety, autonomous workflow protection and secure AI deployment.

Python

dash: a manual Refresh control 2 months ago

enhancement good first issue level-2

fu351/Doberman-Core

111

Doberman is an AI agent security framework for guardrails, prompt injection defense, runtime policy enforcement, tool-use permissions, agent monitoring, audit logs, LLM safety, autonomous workflow protection and secure AI deployment.

Python

doctor: report whether the `dash` and `tui` optional extras are installed 2 months ago

enhancement good first issue level-3

fu351/Doberman-Core

111

Doberman is an AI agent security framework for guardrails, prompt injection defense, runtime policy enforcement, tool-use permissions, agent monitoring, audit logs, LLM safety, autonomous workflow protection and secure AI deployment.

Python

doctor: add a "Password" row next to the 2FA row 2 months ago

enhancement good first issue level-3

fu351/Doberman-Core

111

Doberman is an AI agent security framework for guardrails, prompt injection defense, runtime policy enforcement, tool-use permissions, agent monitoring, audit logs, LLM safety, autonomous workflow protection and secure AI deployment.

Python

cli: `tune --json` is the one JSON command that isn't compact 2 months ago

bug good first issue level-2

fu351/Doberman-Core

111

Doberman is an AI agent security framework for guardrails, prompt injection defense, runtime policy enforcement, tool-use permissions, agent monitoring, audit logs, LLM safety, autonomous workflow protection and secure AI deployment.

Python

cli: `install-hooks --dry-run` previews `doberman dashboard`, but writes `doberman session-summary` 2 months ago

bug good first issue level-2

fu351/Doberman-Core

111

Doberman is an AI agent security framework for guardrails, prompt injection defense, runtime policy enforcement, tool-use permissions, agent monitoring, audit logs, LLM safety, autonomous workflow protection and secure AI deployment.

Python

cli: `doberman log` columns shift for `network_request` and `package_install` rows 2 months ago

bug good first issue level-2

fu351/Doberman-Core

111

Doberman is an AI agent security framework for guardrails, prompt injection defense, runtime policy enforcement, tool-use permissions, agent monitoring, audit logs, LLM safety, autonomous workflow protection and secure AI deployment.

Python

docs: four "(a later slice)" comments describe features that shipped; delete them 2 months ago

documentation good first issue level-1

fu351/Doberman-Core

111

Doberman is an AI agent security framework for guardrails, prompt injection defense, runtime policy enforcement, tool-use permissions, agent monitoring, audit logs, LLM safety, autonomous workflow protection and secure AI deployment.

Python

docs: add an index page for docs/ 2 months ago

documentation good first issue level-1

fu351/Doberman-Core

111

Doberman is an AI agent security framework for guardrails, prompt injection defense, runtime policy enforcement, tool-use permissions, agent monitoring, audit logs, LLM safety, autonomous workflow protection and secure AI deployment.

Python

Passkeys / WebAuthn as a stronger local 2FA tier 2 months ago

enhancement help wanted roadmap level-10

fu351/Doberman-Core

111

Doberman is an AI agent security framework for guardrails, prompt injection defense, runtime policy enforcement, tool-use permissions, agent monitoring, audit logs, LLM safety, autonomous workflow protection and secure AI deployment.

Python

Prove parity cell: gitignored-delete gate (AN-1) on Codex 2 months ago

good first issue level-3 parity

fu351/Doberman-Core

111

Doberman is an AI agent security framework for guardrails, prompt injection defense, runtime policy enforcement, tool-use permissions, agent monitoring, audit logs, LLM safety, autonomous workflow protection and secure AI deployment.

Python

test: prove the data-class rule's documented non-detections (OTP codes, undashed SSNs) 2 months ago

good first issue level-3

fu351/Doberman-Core

111

Doberman is an AI agent security framework for guardrails, prompt injection defense, runtime policy enforcement, tool-use permissions, agent monitoring, audit logs, LLM safety, autonomous workflow protection and secure AI deployment.

Python

research: what does a screen reader announce for the AUTH approval dialog? 2 months ago

help wanted level-4

fu351/Doberman-Core

111

Doberman is an AI agent security framework for guardrails, prompt injection defense, runtime policy enforcement, tool-use permissions, agent monitoring, audit logs, LLM safety, autonomous workflow protection and secure AI deployment.

Python

Merge the whole_script_confusable channel into the Unicode-smuggling harness 2 months ago

enhancement help wanted roadmap level-5

fu351/Doberman-Core

111

Doberman is an AI agent security framework for guardrails, prompt injection defense, runtime policy enforcement, tool-use permissions, agent monitoring, audit logs, LLM safety, autonomous workflow protection and secure AI deployment.

Python

Connector research memo: Cursor interception surfaces 2 months ago

help wanted level-4

fu351/Doberman-Core

111

Doberman is an AI agent security framework for guardrails, prompt injection defense, runtime policy enforcement, tool-use permissions, agent monitoring, audit logs, LLM safety, autonomous workflow protection and secure AI deployment.

Python

Wire the CB.3 loop-anomaly detector into the CB.2 CostObserver seam 2 months ago

enhancement help wanted roadmap level-4

fu351/Doberman-Core

111

Doberman is an AI agent security framework for guardrails, prompt injection defense, runtime policy enforcement, tool-use permissions, agent monitoring, audit logs, LLM safety, autonomous workflow protection and secure AI deployment.

Python

Prove parity cell: read-vs-send fingerprint block on Codex 2 months ago

good first issue level-3 parity

fu351/Doberman-Core

111

Doberman is an AI agent security framework for guardrails, prompt injection defense, runtime policy enforcement, tool-use permissions, agent monitoring, audit logs, LLM safety, autonomous workflow protection and secure AI deployment.

Python

Prove parity cell: approvals are single-use and action-bound on Codex 2 months ago

good first issue level-3 parity

fu351/Doberman-Core

111

Doberman is an AI agent security framework for guardrails, prompt injection defense, runtime policy enforcement, tool-use permissions, agent monitoring, audit logs, LLM safety, autonomous workflow protection and secure AI deployment.

Python

Prove parity cell: gated delete of unrecoverable gitignored data (AN-1) on the MCP proxy 2 months ago

good first issue level-3 parity

fu351/Doberman-Core

111

Doberman is an AI agent security framework for guardrails, prompt injection defense, runtime policy enforcement, tool-use permissions, agent monitoring, audit logs, LLM safety, autonomous workflow protection and secure AI deployment.

Python

feat: add password-gated doberman uninstall command 2 months ago

enhancement help wanted level-5

fu351/Doberman-Core

111

Doberman is an AI agent security framework for guardrails, prompt injection defense, runtime policy enforcement, tool-use permissions, agent monitoring, audit logs, LLM safety, autonomous workflow protection and secure AI deployment.

Python

OpenTelemetry AuditSink 2 months ago

help wanted good first issue level-4

fu351/Doberman-Core

111

Doberman is an AI agent security framework for guardrails, prompt injection defense, runtime policy enforcement, tool-use permissions, agent monitoring, audit logs, LLM safety, autonomous workflow protection and secure AI deployment.

Python

Prove parity cell: tool output carrying credentials is blocked from the model, on the MCP proxy 2 months ago

good first issue level-3 parity

fu351/Doberman-Core

111

Doberman is an AI agent security framework for guardrails, prompt injection defense, runtime policy enforcement, tool-use permissions, agent monitoring, audit logs, LLM safety, autonomous workflow protection and secure AI deployment.

Python

Prove parity cell: control-plane self-protection on OpenClaw 2 months ago

good first issue level-3 parity

fu351/Doberman-Core

111

Doberman is an AI agent security framework for guardrails, prompt injection defense, runtime policy enforcement, tool-use permissions, agent monitoring, audit logs, LLM safety, autonomous workflow protection and secure AI deployment.

Python

cli: one message-severity vocabulary (error:/warning:/note:) instead of four 2 months ago

good first issue level-3

fu351/Doberman-Core

111

Doberman is an AI agent security framework for guardrails, prompt injection defense, runtime policy enforcement, tool-use permissions, agent monitoring, audit logs, LLM safety, autonomous workflow protection and secure AI deployment.

Python

auth: make the challenge prompt pure ASCII (arrow + em-dash in _challenge_message) 2 months ago

good first issue level-2

fu351/Doberman-Core

111

Doberman is an AI agent security framework for guardrails, prompt injection defense, runtime policy enforcement, tool-use permissions, agent monitoring, audit logs, LLM safety, autonomous workflow protection and secure AI deployment.

Python

dash: light-mode verdict badges are ~4.4:1 on their tinted background - just under AA 2 months ago

good first issue level-3

fu351/Doberman-Core

111

Doberman is an AI agent security framework for guardrails, prompt injection defense, runtime policy enforcement, tool-use permissions, agent monitoring, audit logs, LLM safety, autonomous workflow protection and secure AI deployment.

Python

qa: live-test the secret-egress taint floor under Codex with neutral phrasing 2 months ago

help wanted good first issue level-2

fu351/Doberman-Core

111

Doberman is an AI agent security framework for guardrails, prompt injection defense, runtime policy enforcement, tool-use permissions, agent monitoring, audit logs, LLM safety, autonomous workflow protection and secure AI deployment.

Python

Prove parity cell: gated delete of unrecoverable gitignored data (AN-1) on Claude Code 2 months ago

good first issue level-3 parity

fu351/Doberman-Core

111

Doberman is an AI agent security framework for guardrails, prompt injection defense, runtime policy enforcement, tool-use permissions, agent monitoring, audit logs, LLM safety, autonomous workflow protection and secure AI deployment.

Python

Labeled detection corpus + FPR/TPR benchmark harness 3 months ago

help wanted level-5 good first challenge

fu351/Doberman-Core

111

Doberman is an AI agent security framework for guardrails, prompt injection defense, runtime policy enforcement, tool-use permissions, agent monitoring, audit logs, LLM safety, autonomous workflow protection and secure AI deployment.

Python

docs: make SETUP.md more user-friendly 3 months ago

documentation good first issue level-2

fu351/Doberman-Core

111

Doberman is an AI agent security framework for guardrails, prompt injection defense, runtime policy enforcement, tool-use permissions, agent monitoring, audit logs, LLM safety, autonomous workflow protection and secure AI deployment.

Python

docs: document the shared shape of Doberman's host adapters 3 months ago

documentation enhancement good first issue level-3

fu351/Doberman-Core

111

Doberman is an AI agent security framework for guardrails, prompt injection defense, runtime policy enforcement, tool-use permissions, agent monitoring, audit logs, LLM safety, autonomous workflow protection and secure AI deployment.

Python

ci: add an offline checker for internal Markdown links and anchors 3 months ago

enhancement good first issue level-3

fu351/Doberman-Core

111

Doberman is an AI agent security framework for guardrails, prompt injection defense, runtime policy enforcement, tool-use permissions, agent monitoring, audit logs, LLM safety, autonomous workflow protection and secure AI deployment.

Python

qa: a guided tour of the new UX - put seven fresh improvements through their paces (no code required) 3 months ago

help wanted good first issue level-2

fu351/Doberman-Core

111

Doberman is an AI agent security framework for guardrails, prompt injection defense, runtime policy enforcement, tool-use permissions, agent monitoring, audit logs, LLM safety, autonomous workflow protection and secure AI deployment.

Python

Async / non-blocking auth-challenge mechanism (interface only) 3 months ago

enhancement help wanted roadmap level-9

fu351/Doberman-Core

111

Doberman is an AI agent security framework for guardrails, prompt injection defense, runtime policy enforcement, tool-use permissions, agent monitoring, audit logs, LLM safety, autonomous workflow protection and secure AI deployment.

Python

test: extend the ASCII-only guarantee to cover the two characters that slipped through 3 months ago

good first issue level-2

fu351/Doberman-Core

111

Doberman is an AI agent security framework for guardrails, prompt injection defense, runtime policy enforcement, tool-use permissions, agent monitoring, audit logs, LLM safety, autonomous workflow protection and secure AI deployment.

Python

feat(cli): group --help into rich help panels so setup is findable 3 months ago

enhancement good first issue level-3

fu351/Doberman-Core

111

Doberman is an AI agent security framework for guardrails, prompt injection defense, runtime policy enforcement, tool-use permissions, agent monitoring, audit logs, LLM safety, autonomous workflow protection and secure AI deployment.

Python

feat(cli): status --json and sectioned text output 3 months ago

enhancement good first issue level-3

fu351/Doberman-Core

111

Doberman is an AI agent security framework for guardrails, prompt injection defense, runtime policy enforcement, tool-use permissions, agent monitoring, audit logs, LLM safety, autonomous workflow protection and secure AI deployment.

Python

docs: state the defense-in-depth disclaimer once; drop the SEO keyword footer 3 months ago

documentation good first issue level-2

fu351/Doberman-Core

111

Doberman is an AI agent security framework for guardrails, prompt injection defense, runtime policy enforcement, tool-use permissions, agent monitoring, audit logs, LLM safety, autonomous workflow protection and secure AI deployment.

Python

feat(cli): uninstall-hooks says what it leaves behind; setup names the exit 3 months ago

good first issue level-2

fu351/Doberman-Core

111

Doberman is an AI agent security framework for guardrails, prompt injection defense, runtime policy enforcement, tool-use permissions, agent monitoring, audit logs, LLM safety, autonomous workflow protection and secure AI deployment.

Python

feat(cli): enable shell tab-completion 3 months ago

enhancement good first issue level-2

fu351/Doberman-Core

111

Doberman is an AI agent security framework for guardrails, prompt injection defense, runtime policy enforcement, tool-use permissions, agent monitoring, audit logs, LLM safety, autonomous workflow protection and secure AI deployment.

Python

docs: delete the stale 'a later slice adds install-hooks' sentence from hook docstrings 3 months ago

documentation good first issue level-1

fu351/Doberman-Core

111

Doberman is an AI agent security framework for guardrails, prompt injection defense, runtime policy enforcement, tool-use permissions, agent monitoring, audit logs, LLM safety, autonomous workflow protection and secure AI deployment.

Python

docs: publish an honest OWASP-LLM / NIST-AI-RMF control-coverage matrix 3 months ago

documentation help wanted level-4

fu351/Doberman-Core

111

Doberman is an AI agent security framework for guardrails, prompt injection defense, runtime policy enforcement, tool-use permissions, agent monitoring, audit logs, LLM safety, autonomous workflow protection and secure AI deployment.

Python

cli: scan --json silently ignores --quiet; pin the precedence with a test and a docs line 3 months ago

enhancement good first issue level-3

fu351/Doberman-Core

111

Doberman is an AI agent security framework for guardrails, prompt injection defense, runtime policy enforcement, tool-use permissions, agent monitoring, audit logs, LLM safety, autonomous workflow protection and secure AI deployment.

Python

docs: CLI.md's machine-readable section omits log --jsonl and the scan evidence cap 3 months ago

documentation enhancement good first issue level-1

fu351/Doberman-Core

111

Doberman is an AI agent security framework for guardrails, prompt injection defense, runtime policy enforcement, tool-use permissions, agent monitoring, audit logs, LLM safety, autonomous workflow protection and secure AI deployment.

Python

docs: docs/CLI.md documents only 10 of the CLI's 26 commands 3 months ago

documentation enhancement good first issue level-1

fu351/Doberman-Core

111

Doberman is an AI agent security framework for guardrails, prompt injection defense, runtime policy enforcement, tool-use permissions, agent monitoring, audit logs, LLM safety, autonomous workflow protection and secure AI deployment.

Python

tests: assert docs/REASON_CODES.md gives every ReasonCode a real explanation 3 months ago

enhancement good first issue level-4

fu351/Doberman-Core

111

Doberman is an AI agent security framework for guardrails, prompt injection defense, runtime policy enforcement, tool-use permissions, agent monitoring, audit logs, LLM safety, autonomous workflow protection and secure AI deployment.

Python

tests: assert the objective guardrail's rule-reduction loop is exhaustively raise-only 3 months ago

enhancement good first issue level-3

fu351/Doberman-Core

111

Doberman is an AI agent security framework for guardrails, prompt injection defense, runtime policy enforcement, tool-use permissions, agent monitoring, audit logs, LLM safety, autonomous workflow protection and secure AI deployment.

Python

cli: add redaction-safe JSON Lines output to doberman log 3 months ago

enhancement good first issue level-4

fu351/Doberman-Core

111

Doberman is an AI agent security framework for guardrails, prompt injection defense, runtime policy enforcement, tool-use permissions, agent monitoring, audit logs, LLM safety, autonomous workflow protection and secure AI deployment.

Python

docs: catalogue every ReasonCode and what it means (docs/REASON_CODES.md) 3 months ago

documentation enhancement good first issue level-2

fu351/Doberman-Core

111

Doberman is an AI agent security framework for guardrails, prompt injection defense, runtime policy enforcement, tool-use permissions, agent monitoring, audit logs, LLM safety, autonomous workflow protection and secure AI deployment.

Python

cli: add a --quiet flag to doberman scan 3 months ago

enhancement good first issue level-2

fu351/Doberman-Core

111

Doberman is an AI agent security framework for guardrails, prompt injection defense, runtime policy enforcement, tool-use permissions, agent monitoring, audit logs, LLM safety, autonomous workflow protection and secure AI deployment.

Python

docs: add a full CLI reference page (docs/CLI.md) 3 months ago

documentation enhancement good first issue level-1

fu351/Doberman-Core

111

Doberman is an AI agent security framework for guardrails, prompt injection defense, runtime policy enforcement, tool-use permissions, agent monitoring, audit logs, LLM safety, autonomous workflow protection and secure AI deployment.

Python

cli: add JSON output to doberman doctor without changing health exits 3 months ago

enhancement good first issue level-3

fu351/Doberman-Core

111

Doberman is an AI agent security framework for guardrails, prompt injection defense, runtime policy enforcement, tool-use permissions, agent monitoring, audit logs, LLM safety, autonomous workflow protection and secure AI deployment.

Python

cli: add deterministic JSON output to doberman scan 3 months ago

enhancement good first issue level-3

fu351/Doberman-Core

111

Doberman is an AI agent security framework for guardrails, prompt injection defense, runtime policy enforcement, tool-use permissions, agent monitoring, audit logs, LLM safety, autonomous workflow protection and secure AI deployment.

Python

cli: add --json output to doberman policy-history 3 months ago

enhancement good first issue level-3

fu351/Doberman-Core

111

Doberman is an AI agent security framework for guardrails, prompt injection defense, runtime policy enforcement, tool-use permissions, agent monitoring, audit logs, LLM safety, autonomous workflow protection and secure AI deployment.

Python

F-Monitor — a warm ambient-monitoring daemon seam for the decision engine 3 months ago

enhancement help wanted roadmap level-10

fu351/Doberman-Core

111

Doberman is an AI agent security framework for guardrails, prompt injection defense, runtime policy enforcement, tool-use permissions, agent monitoring, audit logs, LLM safety, autonomous workflow protection and secure AI deployment.

Python

adapter: guard another agent harness (Aider / OpenAI Codex CLI / Cursor / generic MCP) 3 months ago

enhancement help wanted level-7

fu351/Doberman-Core

111

Doberman is an AI agent security framework for guardrails, prompt injection defense, runtime policy enforcement, tool-use permissions, agent monitoring, audit logs, LLM safety, autonomous workflow protection and secure AI deployment.

Python

tests: smoke-test --help for every Typer command and group 3 months ago

enhancement good first issue level-2

fu351/Doberman-Core

111

Doberman is an AI agent security framework for guardrails, prompt injection defense, runtime policy enforcement, tool-use permissions, agent monitoring, audit logs, LLM safety, autonomous workflow protection and secure AI deployment.

Python

docs: add a targeted-test selection guide for contributors 3 months ago

documentation enhancement good first issue level-1

fu351/Doberman-Core

111

Doberman is an AI agent security framework for guardrails, prompt injection defense, runtime policy enforcement, tool-use permissions, agent monitoring, audit logs, LLM safety, autonomous workflow protection and secure AI deployment.

Python

docs: add troubleshooting for PATH-shadowed Doberman installations 3 months ago

documentation enhancement good first issue

fu351/Doberman-Core

111

Doberman is an AI agent security framework for guardrails, prompt injection defense, runtime policy enforcement, tool-use permissions, agent monitoring, audit logs, LLM safety, autonomous workflow protection and secure AI deployment.

Python

docs: correct Windows virtual environment activation commands 3 months ago

documentation enhancement good first issue

fu351/Doberman-Core

111

Doberman is an AI agent security framework for guardrails, prompt injection defense, runtime policy enforcement, tool-use permissions, agent monitoring, audit logs, LLM safety, autonomous workflow protection and secure AI deployment.

Python

Policy-as-code — versioned policy files checked into a repo 3 months ago

enhancement good first issue roadmap

fu351/Doberman-Core

111

Doberman is an AI agent security framework for guardrails, prompt injection defense, runtime policy enforcement, tool-use permissions, agent monitoring, audit logs, LLM safety, autonomous workflow protection and secure AI deployment.

Python

rule: extend CI/CD-config protection beyond GitHub Actions (GitLab, Jenkins, CircleCI, Azure Pipelines) 3 months ago

enhancement good first issue

fu351/Doberman-Core

111

Doberman is an AI agent security framework for guardrails, prompt injection defense, runtime policy enforcement, tool-use permissions, agent monitoring, audit logs, LLM safety, autonomous workflow protection and secure AI deployment.

Python

tests: property-based (Hypothesis) laws for the raise-only combine() 4 months ago

help wanted good first issue

fu351/Doberman-Core

111

Doberman is an AI agent security framework for guardrails, prompt injection defense, runtime policy enforcement, tool-use permissions, agent monitoring, audit logs, LLM safety, autonomous workflow protection and secure AI deployment.

Python

cli: add a 'doberman doctor' self-check command 4 months ago

enhancement good first issue

fu351/Doberman-Core

111

Doberman is an AI agent security framework for guardrails, prompt injection defense, runtime policy enforcement, tool-use permissions, agent monitoring, audit logs, LLM safety, autonomous workflow protection and secure AI deployment.

Python

secrets: add Azure & GCP service-account key patterns to the built-in detector 4 months ago

enhancement good first issue

fu351/Doberman-Core

111

Doberman is an AI agent security framework for guardrails, prompt injection defense, runtime policy enforcement, tool-use permissions, agent monitoring, audit logs, LLM safety, autonomous workflow protection and secure AI deployment.

Python

examples: add a tutorial custom-Guardrail plugin package 4 months ago

documentation enhancement help wanted

fu351/Doberman-Core

111

Doberman is an AI agent security framework for guardrails, prompt injection defense, runtime policy enforcement, tool-use permissions, agent monitoring, audit logs, LLM safety, autonomous workflow protection and secure AI deployment.

Python

docs: add a CONTRIBUTING.md to onboard new contributors 4 months ago

documentation good first issue

fu351/Doberman-Core

111

Doberman is an AI agent security framework for guardrails, prompt injection defense, runtime policy enforcement, tool-use permissions, agent monitoring, audit logs, LLM safety, autonomous workflow protection and secure AI deployment.

Python

QA: thoroughly test everything merged to main after 2026-06-20 (#18, #21, #26–#29) 4 months ago

help wanted

fu351/Doberman-Core

111

Doberman is an AI agent security framework for guardrails, prompt injection defense, runtime policy enforcement, tool-use permissions, agent monitoring, audit logs, LLM safety, autonomous workflow protection and secure AI deployment.

Python

Review request: PR #47 (red-team gate ratchet + channel coverage) — ready, needs a peer to merge 4 months ago

help wanted

fu351/Doberman-Core

111

Doberman is an AI agent security framework for guardrails, prompt injection defense, runtime policy enforcement, tool-use permissions, agent monitoring, audit logs, LLM safety, autonomous workflow protection and secure AI deployment.

Python

Review request: PR #54 — Windows onboarding crash fix (encode-safe CLI output) 4 months ago

help wanted

fu351/Doberman-Core

111

Doberman is an AI agent security framework for guardrails, prompt injection defense, runtime policy enforcement, tool-use permissions, agent monitoring, audit logs, LLM safety, autonomous workflow protection and secure AI deployment.

Python

Review request: host-hooks stack HK.1-HK.5.1 (PRs #32->#44) — all ready, needs a peer to review + merge 4 months ago

help wanted

fu351/Doberman-Core

111

Doberman is an AI agent security framework for guardrails, prompt injection defense, runtime policy enforcement, tool-use permissions, agent monitoring, audit logs, LLM safety, autonomous workflow protection and secure AI deployment.

Python

hosthooks: PreToolUse cwd="." fallback may load the wrong strictness mode (HK.1) 4 months ago

help wanted

fu351/Doberman-Core

111

Doberman is an AI agent security framework for guardrails, prompt injection defense, runtime policy enforcement, tool-use permissions, agent monitoring, audit logs, LLM safety, autonomous workflow protection and secure AI deployment.

Python

tests(hosthooks): isolate test_interactive_global_flag_overrides_prompt — it writes to the real ~/.claude/settings.json 4 months ago

help wanted

fu351/Doberman-Core

111

Doberman is an AI agent security framework for guardrails, prompt injection defense, runtime policy enforcement, tool-use permissions, agent monitoring, audit logs, LLM safety, autonomous workflow protection and secure AI deployment.

Python

rule-lab: harden the acceptance gate — bound --eps-fpr and enforce tune/holdout disjointness 4 months ago

help wanted

fu351/Doberman-Core

111

Doberman is an AI agent security framework for guardrails, prompt injection defense, runtime policy enforcement, tool-use permissions, agent monitoring, audit logs, LLM safety, autonomous workflow protection and secure AI deployment.

Python

tests(ood): add red-team corpus entries for invisible_only and unpaired_surrogate channels 4 months ago

help wanted

fu351/Doberman-Core

111

Doberman is an AI agent security framework for guardrails, prompt injection defense, runtime policy enforcement, tool-use permissions, agent monitoring, audit logs, LLM safety, autonomous workflow protection and secure AI deployment.

Python

fu351/Doberman-Core

Open Issues Need Help