ripple
Pass
Audited by Gen Agent Trust Hub on Sep 5, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill provides purely instructional guidelines for an AI agent to analyze UX and design impacts. No malicious code, command execution, or data exfiltration patterns were detected in the instructions or metadata.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted external data in the form of design context and user-proposed changes.
- Ingestion points: The agent reads user-provided project context and design change descriptions (SKILL.md).
- Boundary markers: None specified in the instructions.
- Capability inventory: No capabilities for file system writing, subprocess execution, or network access are present.
- Sanitization: No specific sanitization or filtering logic is requested for the input data.
Audit Metadata