Skills
skills/mxyhi/ok-skills/gh-fix-ci/Gen Agent Trust Hub

gh-fix-ci

Pass

Audited by Gen Agent Trust Hub on Mar 17, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes untrusted data from GitHub Action logs, creating a surface for indirect prompt injection.\n
  • Ingestion points: scripts/inspect_pr_checks.py fetches logs from GitHub via gh run view and the GitHub API (file: scripts/inspect_pr_checks.py).\n
  • Boundary markers: The prompt instructions do not specify the use of delimiters or 'ignore' instructions for the external log content (file: SKILL.md).\n
  • Capability inventory: The agent is capable of modifying repository files and executing commands to implement fixes after receiving user approval (file: SKILL.md).\n
  • Sanitization: Log snippets are extracted and presented to the agent without sanitization or filtering of potential malicious instructions (file: scripts/inspect_pr_checks.py).
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 17, 2026, 02:00 AM