add-ai-captions
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 for the user to connect a remote Model Context Protocol (MCP) server from
https://connect.clueso.io/mcp. This is the primary mechanism for the skill to interact with the Clueso platform. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data in the form of video audio and manual scripts to generate transcripts.
- Ingestion points: Audio tracks from uploaded video files and text-based source scripts provided by users.
- Boundary markers: The instructions do not define specific delimiters to separate transcribed text from agent instructions.
- Capability inventory: Project structure reading, file metadata analysis, text element creation, video rendering, and export functions performed via the connected MCP tools.
- Sanitization: No specific sanitization or filtering of transcribed text is described before it is processed into timed text elements.
Audit Metadata