p-video

Pass

Audited by Gen Agent Trust Hub on Aug 12, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADS
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructions include commands to install the belt CLI and supplemental skills from the belt-sh and inference-sh GitHub organizations. These sources correspond to the official repositories of the service provider used by the skill.- [INDIRECT_PROMPT_INJECTION]: The skill accepts user-provided text prompts and external URLs (images and audio) to be processed by the video generation models.
  • Ingestion points: Prompt and media URL fields within the JSON input for the belt app run command in SKILL.md.
  • Boundary markers: Inputs are encapsulated within a structured JSON object passed to the CLI.
  • Capability inventory: The skill environment is restricted to the belt command via the Bash tool, limiting the impact of potentially malicious inputs.
  • Sanitization: The skill relies on the inference.sh platform's CLI for validation of generated inputs.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 12, 2026, 10:40 PM
Security Audit — agent-trust-hub — p-video