talking-head-production

Pass

Audited by Gen Agent Trust Hub on Sep 2, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the belt CLI tool for video production tasks. The allowed-tools configuration Bash(belt *) effectively restricts the agent's shell execution capabilities to only this specific command, adhering to the principle of least privilege.
  • [EXTERNAL_DOWNLOADS]: The skill references installation documentation and resources hosted on the inference-sh GitHub repository. These references are essential for the operation of the described toolset and originate from the service provider's official infrastructure.
  • [INDIRECT_PROMPT_INJECTION]: The skill defines a workflow where user-supplied text is used to generate video output, representing a standard injection surface.
  • Ingestion points: Untrusted data enters the context via voice_script and voice_prompt parameters in SKILL.md.
  • Boundary markers: The skill does not currently implement specific delimiters or instructions to ignore embedded commands within the input text.
  • Capability inventory: The skill possesses command execution capabilities via belt app run as documented in SKILL.md.
  • Sanitization: No explicit validation or escaping of the user-provided text is performed before being passed to the CLI tool.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 2, 2026, 02:20 PM
Security Audit — agent-trust-hub — talking-head-production