github-release-notes-writer
Pass
Audited by Gen Agent Trust Hub on Aug 5, 2026
Risk Level: SAFE
Full Analysis
- [DATA_EXFILTRATION]: The skill includes explicit instructions to scrub sensitive data, including absolute local paths, credentials, and private hosts, from the final release notes draft before handoff or publication, which effectively mitigates information disclosure risks.
- [COMMAND_EXECUTION]: The skill utilizes standard version control and repository management tools (git and gh CLI) to perform read-only discovery of tags, commits, and pull requests. Write operations to GitHub releases are gated by a requirement for explicit user authorization, ensuring the user maintains control over external repository modifications.
- [PROMPT_INJECTION]: While the skill processes potentially untrusted data from pull request titles and descriptions, it implements defensive practices by requiring the agent to verify all claims against the repository's final code and documentation rather than relying solely on external metadata. The instructions do not contain patterns aimed at bypassing safety filters or overriding core agent behavior.
Audit Metadata