changelog-generator
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data sources which could contain malicious instructions designed to manipulate the agent's output or behavior.
- Ingestion points: Git commit history (messages) and user-defined style files like
CHANGELOG_STYLE.mdare ingested into the agent's context (SKILL.md). - Boundary markers: The instructions do not define specific delimiters or "ignore instructions" markers to isolate the untrusted commit data from the primary agent instructions.
- Capability inventory: The skill possesses capabilities to read git repository history and write output to the local filesystem (
CHANGELOG.md). - Sanitization: No sanitization, validation, or escaping logic is described for the incoming commit strings or external style guidelines.
Audit Metadata