xcodebuildmcp-tool-contract-review — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited xcodebuildmcp-tool-contract-review (Agent Skill) and scored it 45/100 (orange). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 1 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 1 flagged
A base64 string of 128+ characters appears in a documentation file. Encoded prompt injection hides the hostile instruction in base64 — invisible to keyword filters — and relies on the agent's ability to decode it at runtime. There is no normal authoring reason to embed a multi-hundred-byte base64 blob in skill docs.
*.sig, SIGNATURES) outside the documentation.Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
Review guardrails for tool contract changes across implementation, manifests, and workflow exposure.
src/mcp/tools/**manifests/tools/*.yamlmanifests/workflows/*.yamlsrc/core/manifest/schema.tssrc/runtime/tool-catalog.tssrc/runtime/types.tsxcodebuildmcp.com/app/docs/_content/tool-authoring.mdxxcodebuildmcp.com/app/docs/_content/architecture-manifest-visibility.mdxid matches filename.module points to implementation path without extension.schema and handler.names.mcp remains globally unique.names.cli stays workflow-local and consistent with CLI docs/fixtures.outputSchema is present for tools that set ctx.structuredOutput.nextSteps.toolId references existing manifest tool IDs.npm run typechecknpm test -- src/core/manifest/__tests__/schema.test.tsnpm test -- src/runtime/__tests__/tool-invoker.test.tsnpx skill-check .agents/skills/xcodebuildmcp-tool-contract-review~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.