draft-commit-message
Pass
Audited by Gen Agent Trust Hub on Aug 27, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references and fetches commit message guidelines from the author's repository on GitHub (github.com/mtngtools/agents).
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted code changes to draft commit messages, creating a surface where embedded instructions could influence the output.
- Ingestion points: Code changes and git logs as described in SKILL.md.
- Boundary markers: Absent; no delimiters are used to wrap the input data.
- Capability inventory: Limited to drafting and outputting text.
- Sanitization: Absent; no filtering or escaping of input data is performed.
Audit Metadata