alterlab-cdm-preproduction
Pass
Audited by Gen Agent Trust Hub on Apr 5, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted project files like screenplays and director's notes which could contain embedded instructions. 1. Ingestion points: screenplay files and director's notes referenced in SKILL.md. 2. Boundary markers: none identified to isolate content from instructions. 3. Capability inventory: web search, file read, and file write operations defined in SKILL.md. 4. Sanitization: no content sanitization procedures are mentioned.
- [COMMAND_EXECUTION]: The agent autonomously generates production documents including shot lists and schedules as markdown files in the project directory.
- [SAFE]: No malicious patterns, hidden code, or unauthorized network operations were detected. The skill operates according to its stated cinematic purpose and enforces production safety rules.
Audit Metadata