recordings-to-training-module

Pass

Audited by Gen Agent Trust Hub on Jul 10, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill provides the specific command required for the user to install the Clueso MCP connector (claude mcp add --transport http Clueso https://connect.clueso.io/mcp). This is a standard setup procedure for enabling required vendor tools in the assistant's environment.
  • [EXTERNAL_DOWNLOADS]: The skill references external setup guides and service endpoints hosted on the vendor's domains (help.clueso.io and connect.clueso.io). These represent normal integration with the vendor's infrastructure.
  • [PROMPT_INJECTION]: Indirect Prompt Injection Surface (Category 8):
  • Ingestion points: The skill transcribes and analyzes the content of user-uploaded recordings to ensure consistency and alignment with learning goals (SKILL.md, Step 4).
  • Boundary markers: No explicit boundary markers or instructions to ignore embedded commands are specified for the transcription process.
  • Capability inventory: The skill utilizes the Clueso MCP to create projects, add clips, generate narration, and export videos (SKILL.md, Steps 3, 9, and 11).
  • Sanitization: No specific validation or filtering of transcript content is mentioned.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 10, 2026, 09:42 AM
Security Audit — agent-trust-hub — recordings-to-training-module