science-style-animation
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 agent to guide the user through connecting an external Model Context Protocol (MCP) server from the vendor's domain at
https://connect.clueso.io/mcp. This is a standard setup procedure for accessing the skill's primary functionality. - [INDIRECT_PROMPT_INJECTION]: The skill represents a surface for indirect prompt injection by processing external user-supplied data to generate educational content.
- Ingestion points: The skill accepts user-provided "Source material" (documents, articles, or SME notes) as described in the
Inputssection ofSKILL.md. - Boundary markers: There are no explicit delimiters or instructions for the agent to disregard potential commands embedded within the source material.
- Capability inventory: The skill uses Clueso MCP tools to generate visual diagrams, synthesize narration, and export video projects.
- Sanitization: No sanitization or validation steps are defined for the input data before it is interpolated into the workflow for script and scene generation.
Audit Metadata