om-auto-update-changelog
Pass
Audited by Gen Agent Trust Hub on Sep 5, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes potentially untrusted data from pull request bodies and repository configurations. It mitigates this surface by implementing an 'Untrusted content boundary' in references/agentic-setup.md, which explicitly directs the agent to ignore embedded instructions and validate all external values before use.
- [COMMAND_EXECUTION]: Shell and git commands are used for repository analysis. These are strictly confined to the project directory and follow established tracker descriptors, ensuring no unauthorized system access.
- [DATA_EXPOSURE]: The skill implements a 'Secrets hygiene' rule in references/rules.md that redacts credentials and prevents sensitive environment data from being included in changelogs or reports.
Audit Metadata