apple-doc-research

Pass

Audited by Gen Agent Trust Hub on Jul 7, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill provides structured instructions for researching Apple developer platforms using specialized tools. No malicious behaviors, obfuscation, or data exfiltration patterns were identified.
  • [PROMPT_INJECTION]: The skill exhibits an architectural surface for indirect prompt injection as it processes external documentation content. 1. Ingestion points: Documentation and video data enter the agent context via the get_apple_doc_content and get_wwdc_video tools. 2. Boundary markers: There are no explicit delimiters or instructions to disregard potential commands found within the retrieved documentation. 3. Capability inventory: The skill's capabilities are restricted to documentation-specific MCP tools; it does not define subprocess, file-writing, or network execution functions. 4. Sanitization: No sanitization or filtering of the retrieved content is specified before it is presented to the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 7, 2026, 09:26 AM
Security Audit — agent-trust-hub — apple-doc-research