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 Bash tool for git operations and the Write tool 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
Risk Level
SAFE
Analyzed
Aug 11, 2026, 10:51 PM
Security Audit — agent-trust-hub — create-release-notes