invideo-generate
Pass
Audited by Gen Agent Trust Hub on Nov 10, 2026
Risk Level: SAFE
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill directs the agent to official Invideo documentation at https://docs.invideo.io/reference/models for up-to-date model information and pricing. This is a neutral reference to vendor-controlled resources.\n- [INDIRECT_PROMPT_INJECTION]: The skill defines a data ingestion surface by allowing the agent to process user-provided media (images, video, audio) as references. It provides mitigation strategies, such as using specific named tokens (e.g., @ImageN) and double quotes for dialogue, to help the agent distinguish between user data and system instructions.\n- [COMMAND_EXECUTION]: The skill instructs the agent to use standard Invideo command-line tools (invideo gen, find_models, media) to perform generation and metadata retrieval, which is the intended use of the skill within the vendor's ecosystem.
Audit Metadata