qualaroo-automation
Fail
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: HIGHPROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- Indirect Prompt Injection (HIGH): The skill presents a high-risk attack surface for indirect prompt injection when processing untrusted external content.
- Ingestion points: Processes external survey data and response content from the Qualaroo platform.
- Boundary markers: No delimiters or 'ignore instructions' warnings are defined to isolate untrusted data.
- Capability inventory: Uses
RUBE_MULTI_EXECUTE_TOOLandRUBE_REMOTE_WORKBENCHwhich allow for arbitrary tool execution and side effects based on processed content. - Sanitization: No input validation or sanitization mechanisms are described for the data received from Qualaroo.
- Unverifiable Dependencies (MEDIUM): The skill directs the user to add
https://rube.app/mcpas an MCP server. This endpoint is not a recognized trusted source and could serve malicious tool schemas or execution plans.
Recommendations
- AI detected serious security threats
Audit Metadata