skills/vosjs/skills/vos-footage/Gen Agent Trust Hub

vos-footage

Pass

Audited by Gen Agent Trust Hub on Sep 2, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute various vos CLI commands, such as record, render, validate, and push, to automate a video production workflow.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes an actions.json file to guide the vos record command, creating a surface for indirect instructions.
  • Ingestion points: actions.json (referenced in SKILL.md).
  • Boundary markers: None specified for the input file content.
  • Capability inventory: Subprocess execution via vos CLI tools for recording and file management.
  • Sanitization: The instructions do not define methods for validating or escaping the contents of the configuration file.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 2, 2026, 07:25 AM
Security Audit — agent-trust-hub — vos-footage