claude-cookbooks
Pass
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: LOW
Full Analysis
- [SAFE] (SAFE): No malicious patterns, prompt injections, or security vulnerabilities were detected in the analyzed file.
- [EXTERNAL_DOWNLOADS] (INFO): The skill references the official Anthropic Claude Cookbooks repository on GitHub (
github.com/anthropics/claude-cookbooks). Per the [TRUST-SCOPE-RULE],anthropicsis a trusted organization, and the reference is informational. - [CREDENTIALS_UNSAFE] (INFO): Code examples include references to API keys but utilize safe placeholders like
"your-api-key". No hardcoded credentials or secrets are present. - [INDIRECT_PROMPT_INJECTION] (INFO): While the skill provides guidance on processing external data (RAG, Vision), the skill itself acts as a static reference and does not ingest or process untrusted external data in a way that creates an active attack surface.
Audit Metadata