trusty-search

Pass

Audited by Gen Agent Trust Hub on May 14, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill implements its stated code search functionality without any detected malicious patterns or unauthorized network communications. All network operations target localhost (127.0.0.1), which is a whitelisted network destination.
  • [PROMPT_INJECTION]: The skill facilitates processing external codebase data which introduces an indirect prompt injection surface, particularly through the chat tool which synthesizes answers from retrieved code snippets.
  • Ingestion points: Files and directories indexed via the create_index, reindex, and index_file tools.
  • Boundary markers: None identified in the prompt instructions to delimit indexed content or warn the agent about embedded instructions.
  • Capability inventory: Includes file system indexing tools and search/chat tools interacting with a local daemon at 127.0.0.1:7878.
  • Sanitization: No content sanitization or validation is described for the indexed data.
Audit Metadata
Risk Level
SAFE
Analyzed
May 14, 2026, 06:41 PM
Security Audit — agent-trust-hub — trusty-search