gen-changelog
Pass
Audited by Gen Agent Trust Hub on Jul 1, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes
git log main..HEAD --onelineandgit diff main..HEAD --statto analyze commit history and code changes. - [COMMAND_EXECUTION]: The skill runs a local Node.js script
node docs/scripts/sync-changelog.mjsto synchronize documentation across different files. - [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it processes untrusted data from git logs and diffs.
- Ingestion points: Git commit messages and code diff output processed during analysis (SKILL.md).
- Boundary markers: Absent; the agent is instructed to directly interpret the output of git commands.
- Capability inventory: File system write access (updating CHANGELOG.md and documentation files) and command execution (Node.js script).
- Sanitization: Not specified in the instructions.
Audit Metadata