ai-video-generation
Pass
Audited by Gen Agent Trust Hub on Mar 7, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the Bash tool to execute the infsh CLI. This permission is restricted specifically to the vendor's utility, minimizing the risk of arbitrary shell command execution.
- [EXTERNAL_DOWNLOADS]: The documentation provides instructions to install the infsh CLI and additional skills from the inference-sh organization. These are vendor-owned resources required for the skill to function and are documented neutrally.
- [PROMPT_INJECTION]: The skill contains an indirect prompt injection surface as it processes user-provided prompts and media URLs.
- Ingestion points: User-defined 'prompt', 'image_url', and 'audio_url' parameters used in the infsh app run commands.
- Boundary markers: Input data is encapsulated within a structured JSON format passed as a command argument.
- Capability inventory: The skill is authorized to run the infsh CLI tool using the Bash capability.
- Sanitization: No explicit sanitization or content filtering logic is defined within the skill instructions.
Audit Metadata