Movie
Pass
Audited by Gen Agent Trust Hub on Nov 11, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill documentation includes numerous examples of
ffmpegandimagemagickcommands for video editing, format conversion, and frame analysis. These are standard utility commands that support the skill's primary purpose of movie production. - [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided screenplays to generate production assets, creating a vulnerability surface. * Ingestion points: Screenplay and treatment files (e.g.,
script.md). * Boundary markers: The skill does not explicitly define delimiters or specific instructions to separate script content from generation instructions. * Capability inventory: The skill uses subprocess calls toffmpegandmontagefor media processing across multiple workflow stages. * Sanitization: No specific sanitization or filtering of script content is mentioned before interpolation into generation prompts. Despite this surface, the process is oriented toward creative media generation with multiple human-in-the-loop verification checkpoints (animatics, checklists) to mitigate unintended outcomes.
Audit Metadata