anthropic-product-knowledge

Pass

Audited by Gen Agent Trust Hub on Jun 17, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill functions as a navigational guide for the agent to ensure response accuracy by referencing official documentation rather than relying on potentially outdated training data. All instructions align with safe operational procedures.
  • [EXTERNAL_DOWNLOADS]: The skill references several official documentation sites (docs.anthropic.com, docs.claude.com) and the official npm registry (npmjs.com) for the @anthropic-ai/claude-code package. These sources are categorized as trusted organizations and well-known services.
  • [INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion of external data by providing links to documentation maps. Because the ingestion points are restricted to official vendor-controlled domains, the risk of malicious content injection through these channels is negligible.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 17, 2026, 02:27 PM
Security Audit — agent-trust-hub — anthropic-product-knowledge