rethink-surveys
Pass
Audited by Gen Agent Trust Hub on May 9, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTIONDATA_EXFILTRATION
Full Analysis
- [SAFE]: No malicious code or suspicious patterns were identified in the skill instructions or reference materials.
- [EXTERNAL_DOWNLOADS]: The skill references the author's public GitHub repository (ooiyeefei/shanghai-lovable-survey) as a resource for developers to view example implementations.
- [PROMPT_INJECTION]: The skill analyzes user-provided survey content. While this is a potential surface for indirect prompt injection, the risk is mitigated by the skill's focus on structured analytical frameworks and deterministic MCP tools.
- [DATA_EXFILTRATION]: The skill recommends using well-known services such as Supabase and Deepgram for survey applications. No unauthorized data exfiltration patterns were found.
Audit Metadata