video-directing
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [Prompt Injection] (SAFE): The role-play instructions define a cinematic director persona and professional guidelines. No attempts to bypass safety filters, extract system prompts, or override core instructions were detected.
- [Data Exposure & Exfiltration] (SAFE): No sensitive file paths, hardcoded credentials, or network-based exfiltration patterns (such as curl, wget, or fetch) were found.
- [Unverifiable Dependencies & Remote Code Execution] (SAFE): The skill does not include any external package dependencies or remote code execution patterns. It consists entirely of markdown instruction files.
- [Indirect Prompt Injection] (SAFE): The skill has an ingestion surface for untrusted user data. 1. Ingestion points: Scene descriptions, shot lists, and dialogue coverage in validations.md. 2. Boundary markers: Absent. 3. Capability inventory: None (no network, file-write, or subprocess capabilities across the skill files). 4. Sanitization: Absent. Because the skill lacks dangerous tools or execution capabilities, the data ingestion surface is evaluated as safe.
Audit Metadata