skills/metamask/skills/create-pr/Gen Agent Trust Hub

create-pr

Pass

Audited by Gen Agent Trust Hub on Sep 11, 2026

Risk Level: SAFE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes git metadata (branch names, file statuses, and diffs) to generate pull request content, which represents an attack surface where untrusted data could influence agent output.
  • Ingestion points: Local git repository state accessed in repos/metamask-mobile.md and referenced sub-skills.
  • Boundary markers: None specified for the interpolated variables.
  • Capability inventory: Shell command execution via gh CLI and pull request creation via user-github MCP server.
  • Sanitization: Content is handled by standard CLI tools and GitHub APIs, though explicit sanitization of the generated PR body is not described.
  • [COMMAND_EXECUTION]: The skill executes standard git and GitHub CLI commands to verify branch status and create pull requests. These operations are limited to the intended functionality of managing a development workflow and require explicit user consent for destructive actions like pushing to origin.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 11, 2026, 07:59 PM
Security Audit — agent-trust-hub — create-pr