xcodebuildmcp-tool-contract-review
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill serves as a checklist and set of guardrails for developers performing code reviews on tool contracts. It includes standard validation commands such as
npm testandnpm run typecheck, which are appropriate for its intended development workflow. - [INDIRECT_PROMPT_INJECTION]: The skill provides instructions for the agent to inspect source code files (
src/mcp/tools/**,manifests/tools/*.yaml) and execute validation commands. While processing untrusted external files can theoretically expose an agent to indirect prompt injection, this is the primary and legitimate purpose of the skill. The risk is considered negligible within the context of standard code review and testing activities.
Audit Metadata