antfu-query
Pass
Audited by Gen Agent Trust Hub on Oct 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill implements a logical interaction framework for requirement gathering and stress-testing user ideas using a design tree approach.
- [INDIRECT_PROMPT_INJECTION]: The skill has an attack surface as it ingests user-provided plans and ideas while maintaining the ability to read local files and code for fact-finding. However, it incorporates a safety checkpoint by instructing the agent to summarize all settled decisions and wait for explicit user confirmation before proceeding with any actions.
- [SAFE]: No obfuscation, unauthorized command execution, or data exfiltration patterns were detected in the instructions.
Audit Metadata