finish-line

Pass

Audited by Gen Agent Trust Hub on Aug 23, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill has an indirect prompt injection attack surface because it ingests untrusted data from pull request titles, descriptions, and comments while possessing the capability to execute commands that modify the repository state.
  • Ingestion points: External data enters the context via gh pr view, gh pr diff, and gh pr view --comments in SKILL.md.
  • Boundary markers: The skill lacks explicit instructions for the agent to treat the pull request content as untrusted or to use delimiters to isolate external text from system instructions.
  • Capability inventory: The agent is granted capabilities to perform impactful actions such as git push, gh pr comment, gh pr close, and branch management as defined in SKILL.md.
  • Sanitization: There is no defined process for validating user-supplied arguments or sanitizing pulled content before it is processed or used to generate repository changes.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 23, 2026, 02:53 PM
Security Audit — agent-trust-hub — finish-line