gh-review-requests
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes a Python script using
uv runand interacts directly with the local environment via thegh(GitHub) CLI to fetch notifications and repository details. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from an external source (GitHub notification and PR metadata). Pull request titles or repository names could contain malicious instructions designed to be parsed by the agent when displaying the final results.
- Ingestion points: Fetches data from
gh api notificationsandgh api repos/{repo}/pulls/{number}. - Boundary markers: The skill does not explicitly define delimiters or instructions to ignore potential commands within the fetched PR titles before displaying them in a markdown table.
- Capability inventory: Uses the
Bashtool to run scripts and CLI commands; outputs results as Markdown to the agent's context. - Sanitization: No specific sanitization or filtering of PR titles is documented before they are rendered in the final output table.
Audit Metadata