skills/varghq/skills/varg-mockups/Gen Agent Trust Hub

varg-mockups

Pass

Audited by Gen Agent Trust Hub on Nov 14, 2026

Risk Level: SAFECOMMAND_EXECUTIONDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill provides instructions for the agent to execute shell commands, specifically for running Google Chrome in headless mode to capture screenshots of the generated storyboard boards and using FFmpeg for image manipulation.- [DYNAMIC_EXECUTION]: Documentation includes a Python script template that performs automated image processing by invoking system binaries via the subprocess module. This involves generating and executing code that interacts with the local file system and external tools.- [INDIRECT_PROMPT_INJECTION]: The skill establishes a workflow where the agent processes feedback notes authored by human reviewers. These notes are ingested into the agent's context through a Copy feedback mechanism, creating an attack surface for indirect prompt injection where malicious instructions could be embedded in the review data.- [EXTERNAL_DOWNLOADS]: The skill references various external cinematography and film reference websites for look-and-feel guidance. It also points to vendor-owned GitHub repositories for additional mockup templates and resources.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 14, 2026, 09:50 PM