changelog-generator
Pass
Audited by Gen Agent Trust Hub on Aug 6, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it ingests and processes git commit history, which often includes untrusted content from various contributors.
- Ingestion points: Commit messages are read from the repository's git history (SKILL.md).
- Boundary markers: The instructions lack specific delimiters or directions to treat commit messages as raw data rather than instructions.
- Capability inventory: The skill requires the agent to read repository history and write to a CHANGELOG.md file on the local filesystem.
- Sanitization: No sanitization or filtering of the commit message text is specified in the skill's instructions.
Audit Metadata