sop-video-and-doc
Pass
Audited by Gen Agent Trust Hub on Sep 26, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill instructions and workflow are consistent with its stated purpose. It provides clear guidance for the user to set up required connectors using official vendor resources.
- [EXTERNAL_DOWNLOADS]: The skill references setup URLs and an MCP server endpoint at
https://connect.clueso.io/mcp. These are legitimate resources owned by the skill's author (clueso) and are necessary for the skill's functionality. - [COMMAND_EXECUTION]: The skill provides a transparent command for the user to add the Clueso tool to their assistant (
claude mcp add). This is a standard setup procedure for agents using the Model Context Protocol. - [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided procedures and recordings. It mitigates potential injection risks by instructing the agent to establish a 'canonical step list' as a source of truth and explicitly requiring the blurring of sensitive data encountered in footage.
Audit Metadata