release-notes-drafter
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from merged PRs and commits to generate release notes, which could allow malicious instructions embedded in that data to influence the agent's behavior.
- Ingestion points: Pull requests and commits as described in the inputs section of SKILL.md.
- Boundary markers: No explicit delimiters or instructions to ignore embedded commands are specified.
- Capability inventory: No executable scripts, network operations, or file system write capabilities are present in this skill.
- Sanitization: No logic for filtering or sanitizing input data is defined.
Audit Metadata