lecture-to-notes
Pass
Audited by Gen Agent Trust Hub on Sep 26, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill provides instructions to connect a Model Context Protocol (MCP) server via "https://connect.clueso.io/mcp". This setup is required for the skill's functionality and points to the vendor's official domain.
- [INDIRECT_PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection as it transcribes and analyzes external lecture recordings. Ingestion points: Video or audio recordings provided by the user (SKILL.md, Workflow Step 3). Boundary markers: None explicitly specified in the instructions. Capability inventory: Authoring articles and capturing project frames via Clueso tools (SKILL.md, Workflow Steps 5-6). Sanitization: Mitigation is provided through mandatory user draft review (Workflow Step 4) and final content validation (Workflow Step 7).
Audit Metadata