create-release-notes
Pass
Audited by Gen Agent Trust Hub on Aug 11, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection by processing external data from git logs and pull request descriptions. \n
- Ingestion points: The skill reads commit messages and pull request descriptions to generate release notes. \n
- Boundary markers: The instructions do not define clear boundaries or delimiters to isolate untrusted commit data from the agent's core instructions. \n
- Capability inventory: The skill uses the
Bashtool for git operations and theWritetool to save files. \n - Sanitization: There is no evidence of sanitization or validation logic to filter out adversarial instructions within the ingested content.
Audit Metadata