gh-fix-ci
Pass
Audited by Gen Agent Trust Hub on May 26, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the official GitHub CLI (
gh) to interact with GitHub repositories. It executes commands to check authentication status, view pull request details, list checks, and fetch workflow run logs. - [PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection by processing external data.
- Ingestion points: The skill ingests untrusted data from GitHub Actions logs in
SKILL.mdvia thegh run view --logcommand. - Boundary markers: There are no delimiters or instructions used to help the agent distinguish between log content and its own core instructions.
- Capability inventory: The skill has the capability to propose and implement code changes in the user's repository (
SKILL.md). - Sanitization: There is no mechanism described for sanitizing or validating the content of the logs before they are summarized and used to generate a fix plan.
Audit Metadata