ai-video-generation
Pass
Audited by Gen Agent Trust Hub on Aug 6, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references external resources including documentation, installation guides, and media assets hosted on the inference.sh domain and its official GitHub repository. It also suggests the installation of supplemental skills like belt-sh/cli and various others from the inference-sh/skills repository. These downloads and references are functional requirements for the video generation capabilities provided and originate from the service provider's own infrastructure.
- [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection due to the way it handles untrusted data.
- Ingestion points: User-provided text prompts and external media URLs (images, audio, video) are passed as input to the belt CLI tool (SKILL.md).
- Boundary markers: Absent. The skill instructions do not provide explicit delimiters or instructions to the agent to treat these inputs strictly as data or to ignore any instructions embedded within them.
- Capability inventory: Execution of shell commands via the belt CLI, which performs network operations and interacts with external API services (SKILL.md).
- Sanitization: Absent. The inputs are interpolated into JSON payloads within shell commands without explicit sanitization or validation steps described in the instruction set.
Audit Metadata