p-video

Pass

Audited by Gen Agent Trust Hub on Sep 14, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: References installation guides and additional skills hosted on the inference.sh GitHub repository and the npm registry for the belt CLI utility.
  • [INDIRECT_PROMPT_INJECTION]:
  • Ingestion points: The skill takes user-supplied prompts, image URLs, and audio URLs as demonstrated in the SKILL.md examples.
  • Boundary markers: Instructions guide the agent to use structured JSON within the CLI input to separate commands from data.
  • Capability inventory: The skill is configured to use the belt command via the Bash tool to perform video generation tasks.
  • Sanitization: Input processing and validation are managed by the belt CLI and the backend Pruna inference platform.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 14, 2026, 11:29 AM
Security Audit — agent-trust-hub — p-video