gh-review-requests
Pass
Audited by Gen Agent Trust Hub on Mar 16, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the
Bashtool to run a local Python script viauvand interacts with the GitHub CLI (gh) to query notifications and repository data for the well-knowngetsentryorganization. - [PROMPT_INJECTION]: The skill is subject to indirect prompt injection risks as it retrieves and displays pull request titles and author information which are externally controlled.
- Ingestion points: Data is ingested via the output of
fetch_review_requests.pyand thegh apifallback commands mentioned in SKILL.md. - Boundary markers: None; external strings are directly rendered into a Markdown table without delimiters or instructions to ignore embedded commands.
- Capability inventory: The agent has access to the
Bashtool, allowing it to execute shell commands and interact with the GitHub API. - Sanitization: There is no evidence of sanitization or validation of the PR titles or author names before they are presented to the agent context.
Audit Metadata