github-ops
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from GitHub issues, pull requests, and workflow runs which are external, potentially untrusted sources.
- Ingestion points: Commands such as
gh issue view,gh pr view, andgh run viewpull data from GitHub into the agent's context. - Boundary markers: The instructions do not define specific delimiters or instructions to ignore embedded commands within the external content.
- Capability inventory: The skill has access to the
Bashtool for command execution and theWritetool for file modification. - Sanitization: There is no evidence of sanitization or filtering logic applied to the external data before processing.
- [EXTERNAL_DOWNLOADS]: The skill includes instructions to install the GitHub CLI via Homebrew (
brew install gh). This uses a well-known package manager to install the official tool for the service the skill interacts with.
Audit Metadata