image-to-video-director
Pass
Audited by Gen Agent Trust Hub on Sep 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is configured to analyze external data sources such as images, files, and URLs provided by users. This exposes a surface for indirect prompt injection. However, the skill provides clear instructions to the agent to treat such external content as untrusted and to disregard any instructions contained within them.
- [COMMAND_EXECUTION]: The skill executes a local Python script,
scripts/validate_motion_plan.py, to validate structured motion plans. The script is a self-contained utility that performs schema and logic checks using standard Python libraries and does not exhibit malicious behavior or network access.
Audit Metadata