AgentPostmortem/Skill-audit

dist and build are skipped, but a bundled script there is what actually runs about 2 hours ago

enhancement help wanted

1

Security scanner for agent skills — flags prompt-injection, dangerous shell, secret access, and exfiltration before you install a Claude/agent Skill. 31 rules, SARIF, zero-dep. npx @royalpinto007/skill-audit

JavaScript

#agent-skills#ai-security#claude#claude-code#llm-security#mcp#prompt-injection#sarif#security-scanner#supply-chain-security

Executable files with no extension are never collected, so a shebang script is invisible about 2 hours ago

bug help wanted

AgentPostmortem/Skill-audit

1

Security scanner for agent skills — flags prompt-injection, dangerous shell, secret access, and exfiltration before you install a Claude/agent Skill. 31 rules, SARIF, zero-dep. npx @royalpinto007/skill-audit

JavaScript

#agent-skills#ai-security#claude#claude-code#llm-security#mcp#prompt-injection#sarif#security-scanner#supply-chain-security

Files over 2 MB are skipped silently, so padding a payload evades the scanner without a word about 2 hours ago

bug help wanted

AgentPostmortem/Skill-audit

1

Security scanner for agent skills — flags prompt-injection, dangerous shell, secret access, and exfiltration before you install a Claude/agent Skill. 31 rules, SARIF, zero-dep. npx @royalpinto007/skill-audit

JavaScript

#agent-skills#ai-security#claude#claude-code#llm-security#mcp#prompt-injection#sarif#security-scanner#supply-chain-security

Prompt-injection rules only run on markdown, so the same text in a .txt or .yaml is never checked about 2 hours ago

bug help wanted

AgentPostmortem/Skill-audit

1

Security scanner for agent skills — flags prompt-injection, dangerous shell, secret access, and exfiltration before you install a Claude/agent Skill. 31 rules, SARIF, zero-dep. npx @royalpinto007/skill-audit

JavaScript

#agent-skills#ai-security#claude#claude-code#llm-security#mcp#prompt-injection#sarif#security-scanner#supply-chain-security

Open Issues Need Help