pr-review-queue

Pass

Audited by Gen Agent Trust Hub on Jul 13, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the GitHub CLI (gh) to interact with GitHub Projects V2. It executes multiple commands including 'gh project field-list' to retrieve dynamic project schema, 'gh project item-add' to link pull requests to the board, and 'gh api graphql' to perform mutations that update item field values.
  • [PROMPT_INJECTION]: The skill processes user-supplied pull request URLs or numbers, which creates a surface for indirect prompt injection. 1. Ingestion points: External PR URL or number input in 'repos/metamask-mobile.md'. 2. Boundary markers: Absent. 3. Capability inventory: The input is directly interpolated into 'gh' CLI commands. 4. Sanitization: No input validation or sanitization logic is present in the instructions.
  • [SAFE]: All operations are targeted at official MetaMask organization resources, and the usage of standard developer tools (gh CLI, GraphQL) is consistent with the skill's stated purpose for pull request management.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 13, 2026, 06:09 PM
Security Audit — agent-trust-hub — pr-review-queue