ai-marketing-videos

Pass

Audited by Gen Agent Trust Hub on Sep 21, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references the installation of the belt-sh/cli tool and provides links to setup documentation on the inference-sh GitHub repository. These resources are part of the intended platform functionality.
  • [COMMAND_EXECUTION]: The instructions contain multiple examples of executing the belt CLI for media generation. The skill restricts the agent's execution environment to this specific tool using the allowed-tools configuration.
  • [INDIRECT_PROMPT_INJECTION]: The complex workflows involve passing the output of a script-writing model into a text-to-speech tool, creating a potential surface for instructions in the script to influence the speech generation. 1. Ingestion points: script.json in the Explainer Video workflow. 2. Boundary markers: None used in the shell examples. 3. Capability inventory: The belt CLI is used for subsequent media generation and merging. 4. Sanitization: None provided in the template scripts.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 21, 2026, 08:14 PM
Security Audit — agent-trust-hub — ai-marketing-videos