commit-poet
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the Bash tool to execute git diff to read code changes and git commit to apply the generated poetic message. These actions are core to the skill's functionality.
- [INDIRECT_PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection by processing untrusted code content from the filesystem. 1. Ingestion points: The skill reads staged or unstaged diffs via git diff commands in Step 2 of SKILL.md. 2. Boundary markers: No delimiters or specific safety instructions are used to separate the code diff from the instruction context. 3. Capability inventory: The skill has access to the Bash tool for shell command execution and the AskUserQuestion tool. 4. Sanitization: Code diff content is not escaped or sanitized before being interpreted by the agent.
- [EXTERNAL_DOWNLOADS]: The README.md provides installation instructions involving npx and a vendor-specific GitHub repository.
Audit Metadata