mobilebuildmcp-tool-contract-review
Pass
Audited by Gen Agent Trust Hub on Oct 16, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external documentation from
xcodebuildmcp.comand various local project files (source code, manifests, and schemas) which could potentially contain embedded instructions. - Ingestion points:
src/mcp/tools/**,manifests/tools/*.yaml,manifests/workflows/*.yaml, and documentation URLs underxcodebuildmcp.com. - Boundary markers: None present in the instructions to separate untrusted content from the system prompt.
- Capability inventory: The skill utilizes
npm run typecheck,npm test, andnpx skill-checkwhich execute code based on the project state. - Sanitization: No explicit sanitization or validation of the ingested file content is performed prior to processing.
- [DYNAMIC_EXECUTION]: The skill instructions include standard development workflow commands such as
npm run typecheck,npm test, andnpx skill-checkto validate the tool contracts. These commands execute code within the project's runtime environment as part of the intended review and verification process. - [EXTERNAL_DOWNLOADS]: The skill references documentation hosted on
xcodebuildmcp.com. These references are informative for the review process and do not involve the execution of remote scripts or unverified binary downloads.
Audit Metadata