deepsearch

Pass

Audited by Gen Agent Trust Hub on Aug 20, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill consists of pure natural language instructions designed to guide an agent through a codebase search workflow. No scripts, executables, or network operations are included.
  • [INDIRECT_PROMPT_INJECTION]:
  • Ingestion points: The skill directs the agent to read file content and imports from the user's codebase (SKILL.md).
  • Boundary markers: No specific delimiters or safety instructions are provided to the agent regarding the content it reads.
  • Capability inventory: The skill itself does not define any capabilities like subprocess calls or network operations; it relies on the agent's standard search tools.
  • Sanitization: No sanitization of the codebase data is described in the instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 20, 2026, 11:36 AM
Security Audit — agent-trust-hub — deepsearch