search-hierarchy

Pass

Audited by Gen Agent Trust Hub on Mar 23, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill provides a search tool hierarchy and decision tree to optimize token usage. Its logic (AST-grep for structure, LEANN for semantics, Grep for literals) is a standard architectural pattern for AI agents and does not involve dangerous operations.
  • [PROMPT_INJECTION]: The skill facilitates the processing of codebase content via search tools, which presents an inherent surface for indirect prompt injection if the searched files contain adversarial instructions. This is a common characteristic of development-oriented skills and is associated with its primary purpose.
  • Ingestion points: Results from AST-grep, LEANN, Grep, and Read tools.
  • Boundary markers: None specified.
  • Capability inventory: Code searching and file reading capabilities.
  • Sanitization: Not specified.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 23, 2026, 09:04 AM
Security Audit — agent-trust-hub — search-hierarchy