query-planning

Pass

Audited by Gen Agent Trust Hub on Sep 8, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [SAFE]: The skill consists entirely of instructional markdown designed to guide the agent's reasoning process for search query decomposition. It does not include any scripts, dependencies, or configuration settings.
  • [INDIRECT_PROMPT_INJECTION]: The skill defines a surface for processing user-supplied research questions. However, the instructions are restricted to text-based planning (concepts, hypotheses, synonyms) and do not involve any risky tool executions or network interactions based on that input.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 8, 2026, 02:01 PM
Security Audit — agent-trust-hub — query-planning