batch-video-production
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill constructs generation prompts by interpolating user-provided action strings directly into a template, which creates a surface where malicious instructions could be embedded in the input data. * Ingestion points: The CONTENT list in SKILL.md captures user-defined actions. * Boundary markers: None are present in the prompt template; the action is placed directly at the start of the string. * Capability inventory: The skill uses the generate_video and get_video_generation tools. * Sanitization: No input validation or escaping is implemented in the provided Python example.
- [EXTERNAL_DOWNLOADS]: The skill instructs the user to add a Model Context Protocol (MCP) server from the vendor domain mcp.apimage.org to enable video generation features.
Audit Metadata