skill-design
Pass
Audited by Gen Agent Trust Hub on Apr 5, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill explicitly instructs the agent to treat all external content found during web research as data only and never to follow instructions embedded in those files. This control prevents the agent from being influenced by potentially malicious code or instructions in public repositories.- [EXTERNAL_DOWNLOADS]: The tool performs searches on GitHub.com to gather design templates and trigger keywords. This activity targets a well-known service and is restricted to retrieving reference data rather than executable code.- [DATA_EXFILTRATION]: No sensitive data access or exfiltration patterns were identified. The skill only processes user-provided goals and public web data to build a specification which is then reviewed by the user before being passed to a creation tool.
Audit Metadata