explainer-video-guide

Pass

Audited by Gen Agent Trust Hub on Jun 19, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Recommends installation of the belt-sh/cli and related production skills from the inference-sh organization on GitHub.
  • [COMMAND_EXECUTION]: Executes the belt command-line utility via Bash to perform remote media generation tasks.
  • [PROMPT_INJECTION]: Implements a workflow where untrusted user input is passed as prompts to generative AI models.
  • Ingestion points: Input fields for video and audio generation commands in SKILL.md.
  • Boundary markers: None specified for user-provided prompt content.
  • Capability inventory: Bash tool access restricted to belt commands.
  • Sanitization: No explicit sanitization or validation of input prompts is performed before execution.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 19, 2026, 02:15 AM
Security Audit — agent-trust-hub — explainer-video-guide