daft-docs-navigation

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill facilitates the cloning of the official Daft source repository (https://github.com/Eventual-Inc/Daft.git) if local documentation is missing, ensuring access to current API references and examples.\n- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external markdown files and the official documentation website, creating a potential surface for instructions embedded in those documents to influence agent behavior.\n
  • Ingestion points: Documentation files in the docs/ directory and content from https://docs.daft.ai.\n
  • Boundary markers: None present.\n
  • Capability inventory: Includes file reading (read), search operations (grep_search), and repository cloning (git clone).\n
  • Sanitization: None present.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 03:19 AM
Security Audit — agent-trust-hub — daft-docs-navigation