self-navigable-sales-demo

Pass

Audited by Gen Agent Trust Hub on Jul 10, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill provides instructions for the agent to install the Clueso MCP connector using the 'claude mcp add' command upon user confirmation. This is a standard and documented setup procedure for the Clueso service.
  • [PROMPT_INJECTION]: The skill features an indirect prompt injection surface. (1) Ingestion points: Transcribing spoken audio from user-provided video files in Step 2. (2) Boundary markers: Absent. (3) Capability inventory: The skill is limited to Clueso-specific video editing functions and does not have access to sensitive system tools or arbitrary code execution. (4) Sanitization: No explicit sanitization of the transcribed audio is mentioned.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 10, 2026, 09:42 AM
Security Audit — agent-trust-hub — self-navigable-sales-demo