recording-to-email-drip-series
Pass
Audited by Gen Agent Trust Hub on Sep 26, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill provides instructions for the agent to offer a setup command (
claude mcp add --transport http Clueso https://connect.clueso.io/mcp) to the user. This is a standard procedure for installing the vendor's Model Context Protocol (MCP) server and requires explicit user confirmation before execution. - [INDIRECT_PROMPT_INJECTION]: The skill ingests and analyzes spoken audio transcripts from user-provided videos to determine topic boundaries and timing. This creates a potential surface for indirect prompt injection if the source media contains adversarial spoken instructions designed to influence the agent's behavior during the analysis phase.
- Ingestion points: Spoken audio transcription from source videos (Workflow Step 2).
- Boundary markers: None defined for transcript analysis.
- Capability inventory: Video splitting, project duplication, and rendering via the Clueso MCP toolset.
- Sanitization: None mentioned for processing audio-to-text data.
Audit Metadata