research-design
Pass
Audited by Gen Agent Trust Hub on Mar 12, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is purely instructional and contains no code or commands.
- [SAFE]: No network access, data exfiltration, or credential use is present.
- [SAFE]: Local file references point to internal documentation for context, which is standard behavior for knowledge-based skills.
- [SAFE]: While the skill ingests user input, it has no dangerous capabilities to exploit, mitigating any risk of indirect prompt injection.
Audit Metadata