knowledge-query

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [SAFE] (SAFE): No security issues detected. The skill contains no executable scripts or commands.
  • [Indirect Prompt Injection] (SAFE): The skill ingests user queries to search a knowledge base. While it lacks explicit sanitization, the risk is minimal due to the restricted 'Read' tool and the skill's narrow operational scope.
  • Ingestion points: User queries defined in the 'Input Requirements' section.
  • Boundary markers: Absent.
  • Capability inventory: Restricted to the 'Read' tool.
  • Sanitization: No sanitization logic provided in the prompt instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:16 PM