recording-to-help-article
Pass
Audited by Gen Agent Trust Hub on Jul 10, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill provides instructions for users to configure the Clueso MCP connector using the command
claude mcp add --transport http Clueso https://connect.clueso.io/mcp. This is a legitimate and documented setup procedure for the vendor's service. - [PROMPT_INJECTION]: The instructions include directives to optimize the user interface by suppressing trivial information, such as not mentioning the workspace selection when only one workspace is available. These are standard UX optimizations and do not involve concealing malicious behavior or bypassing safety protocols.
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from recording transcriptions (Step 2). While this represents a theoretical attack surface for indirect prompt injection, the risk is effectively mitigated by Step 4, which requires the agent to show the draft to the user for explicit confirmation before proceeding with any live article creation or updates.
Audit Metadata