animated-explainer-video
Pass
Audited by Gen Agent Trust Hub on Sep 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest untrusted user-supplied data (product descriptions, audience details, and problem statements) to generate narration scripts and storyboard visual descriptions. This creates a surface where malicious user input could attempt to influence the agent's logic or tool usage patterns.
- Ingestion points: The "Inputs" section (SKILL.md) describes receiving product, feature, and concept descriptions directly from the user.
- Boundary markers: There are no explicit delimiters or "ignore embedded instructions" markers defined for the interpolation of user data into the scripting workflow.
- Capability inventory: The skill involves calling Clueso MCP tools for generating animations and voiceovers and provides external project links for export.
- Sanitization: No sanitization or validation logic is defined for the user-supplied input before it is used to generate the video script beats.
Audit Metadata