explore-and-plan
Pass
Audited by Gen Agent Trust Hub on Oct 11, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill provides instructions for turning project goals into plans. No malicious patterns, obfuscation, or data exfiltration attempts were detected.
- [NO_CODE]: The skill does not contain any scripts, binaries, or automated tasks. It consists purely of markdown documentation, evaluation data, and configuration files.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process user-provided project descriptions. While it lacks specific sanitization logic for these inputs, the absence of file-writing or network-capable tools minimizes the risk of indirect injection attacks.
Audit Metadata