shot-design
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external project files which could contain malicious instructions designed to influence the agent's behavior.
- Ingestion points: Workflow step 1 requires the agent to read external screenplay scenes, director books, line manifests, and dramaturgy rules from the project environment.
- Boundary markers: The instructions do not provide specific boundary markers or "ignore embedded instructions" warnings to separate user-provided screenplay text from the agent's core instructions.
- Capability inventory: The skill is capable of writing data to the filesystem, specifically creating and updating
04_generation/shot_briefs.jsonl(Step 4). - Sanitization: There are no outlined sanitization, validation, or escaping procedures for the external content before it is processed or written back to project files.
Audit Metadata