huashu-motion

Pass

Audited by Gen Agent Trust Hub on Nov 16, 2026

Risk Level: SAFEDYNAMIC_CONTEXT_INJECTIONINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [DYNAMIC_CONTEXT_INJECTION]: The skill contains logic in SKILL.md that instructs the agent to perform an automated version check by executing git ls-remote against a remote repository to compare local and remote tags.
  • [INDIRECT_PROMPT_INJECTION]: The skill's primary workflow involves ingesting untrusted data from external URLs (via om grab) and user comments (via om inbox) to modify the project's source code (index.html). This creates a significant surface for indirect prompt injection attacks where malicious data could influence the agent's code generation.
  • [EXTERNAL_DOWNLOADS]: The skill's helper script bin/om is configured to download and execute the huashu-motion package from the NPM registry using npx. It also provides commands to install external asset packs, such as real-instrument samples via om samples build.
  • [COMMAND_EXECUTION]: The agent is instructed to manage local development environments, including starting a local server on 127.0.0.1 for the 'studio' preview and invoking rendering tools like ffmpeg for video export.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 16, 2026, 08:56 AM