gh-fix-ci

Pass

Audited by Gen Agent Trust Hub on Jun 24, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill relies on the GitHub CLI (gh) and a bundled Python script (scripts/inspect_pr_checks.py) to interact with the repository and GitHub Actions API. It executes commands to check authentication status, view PR details, and fetch job logs.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection via external CI/CD logs.
  • Ingestion points: Fetches GitHub Actions logs and check run summaries via gh commands as described in the workflow section of SKILL.md.
  • Boundary markers: No specific boundary markers or explicit instructions to ignore embedded commands are used when including log snippets in the failure summary.
  • Capability inventory: The skill is designed to propose and implement code changes (Workflow Step 7) and can execute arbitrary gh commands, creating a path from log ingestion to file system modification.
  • Sanitization: The skill does not specify sanitization or validation of the retrieved log content before it is used as context for generating a fix plan.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 24, 2026, 02:10 AM
Security Audit — agent-trust-hub — gh-fix-ci