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 Bash tool to run a local Python script via uv and interacts with the GitHub CLI (gh) to query notifications and repository data for the well-known getsentry organization.
  • [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.py and the gh api fallback 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 Bash tool, 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
Risk Level
SAFE
Analyzed
Mar 16, 2026, 03:15 AM