xcodebuildmcp-rendering-streaming-review
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze external data, including project source code and documentation from
xcodebuildmcp.com. This represents a surface for indirect prompt injection if the ingested content contains adversarial instructions. - Ingestion points: Local source files (
src/**) and external documentation links (xcodebuildmcp.com/app/docs/_content/*). - Boundary markers: Absent.
- Capability inventory: Shell execution via
npm test,npm run, andnpx skill-checkfor validation. - Sanitization: Absent.
- [COMMAND_EXECUTION]: The skill includes instructions to execute shell commands for validation purposes, such as
npm test,npm run test:snapshots,npm run typecheck, andnpx skill-check. These are standard development workflows for the project and do not involve user-controlled input or suspicious parameters. - [EXTERNAL_DOWNLOADS]: The skill references architectural documentation from
xcodebuildmcp.com. These are project-specific documentation resources used for review and do not involve the download of executable scripts or binary payloads.
Audit Metadata