write-pr-description

Pass

Audited by Gen Agent Trust Hub on Sep 5, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided pull request content (titles, descriptions, and code diffs) to generate structured write-ups. There is an inherent risk that malicious instructions embedded in the processed PR content could influence the agent's behavior. \n
  • Ingestion points: The agent reads existing PR titles, descriptions, and repository files via file system tools.\n
  • Boundary markers: The instructions do not specify the use of delimiters or 'ignore' instructions for untrusted input data.\n
  • Capability inventory: The agent is configured with tools including Bash, Write, Edit, and Read.\n
  • Sanitization: No specific input sanitization steps are defined within the skill instructions.\n- [NO_CODE]: The skill consists entirely of markdown-based instructions for the AI agent and does not include any accompanying scripts or executable files.\n- [SAFE]: All instructions are transparent, follow standard development best practices, and do not attempt to bypass safety filters or exfiltrate data.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 5, 2026, 04:31 PM
Security Audit — agent-trust-hub — write-pr-description