changelog-generator
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external data in the form of git commit messages and local style guides, which could contain malicious instructions designed to influence the agent's behavior. Ingestion points: Git commit history and
CHANGELOG_STYLE.md(SKILL.md). Boundary markers: None identified to separate commit data from agent instructions. Capability inventory: The skill performs text generation and suggests writing output to a local file (CHANGELOG.md). Sanitization: No specific sanitization or filtering of commit content is described.
Audit Metadata