gh-review-requests

Pass

Audited by Gen Agent Trust Hub on Sep 9, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes data from GitHub pull requests, such as titles and author names, which are externally controlled and could contain malicious instructions.
  • Ingestion points: GitHub notification API and pull request metadata retrieval.
  • Boundary markers: Results are presented in a structured markdown table.
  • Capability inventory: The skill utilizes the Bash tool to execute gh CLI commands and a local Python script.
  • Sanitization: The instructions do not specify sanitization or escaping for the retrieved GitHub content.
  • [COMMAND_EXECUTION]: The skill executes shell commands to interact with the GitHub API and run a Python script via uv. The agent is instructed to sanitize the team-slug input by converting it to a lowercase-hyphenated format, which reduces the risk of command injection.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 9, 2026, 11:05 PM
Security Audit — agent-trust-hub — gh-review-requests