ugen
Pass
Audited by Gen Agent Trust Hub on Feb 22, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION] (SAFE): The skill is designed to facilitate the use of the
ugenCLI utility for generating images and videos. The documented commands (ugen models,ugen generate) are legitimate and necessary for the skill's stated purpose. - [PROMPT_INJECTION] (LOW): Indirect Prompt Injection Surface. The skill enables the agent to ingest and process untrusted external data (text descriptions and image files) which are then forwarded to LLM providers.
- Ingestion points: CLI parameters
--part text:...and--part image:...defined inSKILL.md. - Boundary markers: No specific delimiters or 'ignore' instructions are provided to the model to mitigate embedded instructions in the user input.
- Capability inventory: The tool executes media generation via external API providers (Gemini, OpenAI, xAI).
- Sanitization: No sanitization or validation of the input content is described in the provided instructions.
Audit Metadata