skills/halt-catch-fire/skills/p-video/Gen Agent Trust Hub

p-video

Pass

Audited by Gen Agent Trust Hub on Aug 3, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill leverages the belt CLI for all operations. It utilizes the allowed-tools frontmatter field to restrict the agent's environment, ensuring it can only execute the belt command via Bash, which significantly reduces the attack surface.- [EXTERNAL_DOWNLOADS]: The documentation contains instructions for the user to install the belt CLI and related skills from standard package sources and GitHub repositories associated with the service provider (inference.sh). These are documented correctly as external dependencies.- [SAFE]: Analysis of the skill instructions and examples shows no signs of prompt injection, obfuscation, or unauthorized data access. The skill's behavior is consistent with its described utility as a video generation tool.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 3, 2026, 03:53 PM
Security Audit — agent-trust-hub — p-video