xcodebuildmcp-runtime-boundary-review
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill directs the agent to access documentation hosted at
xcodebuildmcp.com. This involves making network requests to an external domain that is not included in the standard whitelist of trusted services.\n- [COMMAND_EXECUTION]: The instructions authorize the use of the shell to runnpm test,npm run typecheck, andnpx skill-check. These commands provide the agent with a capability to execute code locally, which could be exploited if the agent follows malicious instructions encountered during the review process.\n- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external URLs and local source code files that could contain adversarial instructions, posing a risk of indirect prompt injection.\n - Ingestion points: External documentation files at
xcodebuildmcp.com/app/docs/_content/and project files insrc/,manifests/, andsrc/cli/directories.\n - Boundary markers: The skill does not provide specific delimiters or instructions to treat the inspected content as untrusted data or to ignore embedded commands.\n
- Capability inventory: The agent has the ability to execute shell commands via
npmandnpxtools.\n - Sanitization: There are no verification steps or sanitization procedures defined for the data being ingested and reviewed.
Audit Metadata