update-release-notes
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill creates an attack surface by ingesting and processing data from external sources like Git history and local documentation files.
- Ingestion points: Git commit messages retrieved via
git logand the content of command documentation files located underdocs/docs/cmd/. - Boundary markers: The instructions do not specify any delimiters or safety markers when interpolating extracted text into the release notes.
- Capability inventory: The skill has the ability to read and write local documentation files and execute shell commands (
git). - Sanitization: No specific sanitization or escaping mechanisms are implemented for the content extracted from commits or documentation before it is written to the release notes file.
Audit Metadata