recording-to-email-drip-series
Pass
Audited by Gen Agent Trust Hub on Jul 10, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to offer or provide shell commands for environment configuration, specifically
claude mcp add --transport http Clueso https://connect.clueso.io/mcp. These are standard procedures for connecting the required Model Context Protocol (MCP) server provided by the vendor. - [EXTERNAL_DOWNLOADS]: References official documentation and setup endpoints hosted on the vendor's domain (
clueso.io) for the purpose of configuring the necessary integration tools. - [PROMPT_INJECTION]: The workflow involves transcribing and analyzing audio from user-provided video recordings. This ingestion of untrusted external data creates a surface for indirect prompt injection, where malicious instructions hidden in the audio could attempt to influence the agent's behavior during the analysis or editing phases.
Audit Metadata