xcodebuildmcp-docs-release-review

Pass

Audited by Gen Agent Trust Hub on Sep 23, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to run standard local development tools including npm run build and npx skill-check to validate documentation and release artifacts. It also executes a project-specific script scripts/generate-github-release-notes.mjs for release note verification.
  • [INDIRECT_PROMPT_INJECTION]: The skill's primary function involves reading content from external Markdown files (README.md, CHANGELOG.md) and project scripts. While this ingestion represents a theoretical attack surface where untrusted text could influence agent behavior, the risk is negligible due to the skill's specific constraints for consistency checking and the context of repository maintenance.
  • Ingestion points: Reads README.md, CHANGELOG.md, and content under xcodebuildmcp.com/app/docs/_content/**.
  • Boundary markers: None present.
  • Capability inventory: Local execution of npm, node, and npx tools.
  • Sanitization: None present.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 23, 2026, 06:08 PM
Security Audit — agent-trust-hub — xcodebuildmcp-docs-release-review