query-sub-agent
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- Indirect Prompt Injection (LOW): The skill processes specification files from the local directory to generate and review code.
- Ingestion points: Specification files located in
docs/specs/{feature-name}/(e.g.,frame.yaml,query.yaml). - Boundary markers: No explicit delimiters or instructions are provided to the agent to treat spec content as untrusted.
- Capability inventory: Generates, modifies, and reviews Query Side application logic and database read models.
- Sanitization: No validation or sanitization of the input specification data is performed.
Audit Metadata