film-shot-generation
Pass
Audited by Gen Agent Trust Hub on Oct 30, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill invokes a local script
scripts/keyframes.pyto process video beat plans and determine keyframe requirements. A detailed review of the script confirms it uses only Python's standard library (json,sys,typing), performs no network operations, and contains no dangerous system-level calls or file system modifications beyond reading the input provided. - [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided content such as shot descriptions, action performances, and repair notes which are used to generate video prompts. This creates a potential surface for indirect prompt injection. However, the skill implements a mandatory verification step using the
picsart_film_verify_prompttool to validate the literal arguments of every prompt against a strict schema and set of rules before any generation occurs. This ensures that user-provided content cannot bypass the intended generation logic or influence the agent's behavior beyond the defined scope.
Audit Metadata