sumamovva/probeagent

Docs: 'Test your <framework> agent in 5 minutes' about 3 hours ago

good first issue

16

Offensive security testing CLI for AI agents — 85 attack strategies (and counting) across 12 categories

Python

#ai-agent#ai-security#llm-security#offensive-security#penetration-testing#prompt-injection#pyrit#red-teaming

Add more --redteam objectives (PyRIT) about 3 hours ago

help wanted

sumamovva/probeagent

16

Offensive security testing CLI for AI agents — 85 attack strategies (and counting) across 12 categories

Python

#ai-agent#ai-security#llm-security#offensive-security#penetration-testing#prompt-injection#pyrit#red-teaming

New attack category: Memory / Context Poisoning about 3 hours ago

help wanted

sumamovva/probeagent

16

Offensive security testing CLI for AI agents — 85 attack strategies (and counting) across 12 categories

Python

#ai-agent#ai-security#llm-security#offensive-security#penetration-testing#prompt-injection#pyrit#red-teaming

Add a target adapter for a popular agent framework about 3 hours ago

help wanted

sumamovva/probeagent

16

Offensive security testing CLI for AI agents — 85 attack strategies (and counting) across 12 categories

Python

#ai-agent#ai-security#llm-security#offensive-security#penetration-testing#prompt-injection#pyrit#red-teaming

Import a public seed corpus (e.g. SafeMTData) via --seeds about 3 hours ago

good first issue

sumamovva/probeagent

16

Offensive security testing CLI for AI agents — 85 attack strategies (and counting) across 12 categories

Python

#ai-agent#ai-security#llm-security#offensive-security#penetration-testing#prompt-injection#pyrit#red-teaming

Add remediation guidance to findings (close the loop) about 3 hours ago

help wanted

sumamovva/probeagent

16

Offensive security testing CLI for AI agents — 85 attack strategies (and counting) across 12 categories

Python

#ai-agent#ai-security#llm-security#offensive-security#penetration-testing#prompt-injection#pyrit#red-teaming

Expand the refusal grader with more phrasings about 3 hours ago

good first issue

sumamovva/probeagent

16

Offensive security testing CLI for AI agents — 85 attack strategies (and counting) across 12 categories

Python

#ai-agent#ai-security#llm-security#offensive-security#penetration-testing#prompt-injection#pyrit#red-teaming

Add a new evasion converter about 3 hours ago

good first issue

sumamovva/probeagent

16

Offensive security testing CLI for AI agents — 85 attack strategies (and counting) across 12 categories

Python

#ai-agent#ai-security#llm-security#offensive-security#penetration-testing#prompt-injection#pyrit#red-teaming

Add a new prompt-injection strategy about 3 hours ago

good first issue

sumamovva/probeagent

16

Offensive security testing CLI for AI agents — 85 attack strategies (and counting) across 12 categories

Python

#ai-agent#ai-security#llm-security#offensive-security#penetration-testing#prompt-injection#pyrit#red-teaming

Open Issues Need Help