xcodebuildmcp-structured-output-review
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to use standard development tools such as
npmandnpxto execute test suites and type-checking routines (npm run test:schema-fixtures,npm test,npm run typecheck,npx skill-check). These are expected behaviors for a development-focused review skill. - [INDIRECT_PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface as it is designed to ingest and review content from repository files and project documentation paths. 1. Ingestion points: Local files in
schemas/,src/, andsrc/snapshot-tests/__fixtures__/json/**, as well as content fromxcodebuildmcp.com. 2. Boundary markers: The skill does not provide specific delimiters or instructions to ignore embedded commands within the reviewed data. 3. Capability inventory: The agent has the capability to execute shell commands vianpmandnpx. 4. Sanitization: No content sanitization or validation routines for external data are specified in the instructions.
Audit Metadata