gh-review-requests
Pass
Audited by Gen Agent Trust Hub on Mar 19, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The script
fetch_review_requests.pyexecutes the GitHub CLI (gh) using thesubprocess.runmethod with list-based arguments. This approach is secure and avoids risks associated with shell command injection. - [PROMPT_INJECTION]: The skill processes data from GitHub, which is an external source, presenting a surface for indirect prompt injection.
- Ingestion points: Pull request titles and author handles are retrieved from the GitHub API and processed by the skill.
- Boundary markers: The output table in
SKILL.mddoes not include boundary markers or warnings for the agent to ignore instructions within the data. - Capability inventory: The skill uses
Bashto run a Python script which uses theghtool for data retrieval. - Sanitization: There is no evidence of sanitization applied to the PR titles or other external metadata before they are displayed to the user.
Audit Metadata