local-cinematic-pipeline
Pass
Audited by Gen Agent Trust Hub on Nov 10, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns or executable code detected in the skill instructions. The content is purely procedural and documentation-oriented.
- [DATA_EXFILTRATION]: The skill configuration emphasizes 'fully local' operations and explicitly mandates that no outbound API keys be required, reducing the risk of accidental data exposure or credential theft.
- [INDIRECT_PROMPT_INJECTION]: The skill defines a surface for processing untrusted user data ('Briefs') which are used to generate media via local workflows. Ingestion points: User brief paragraph described in SKILL.md. Boundary markers: Absent. Capability inventory: Local file writes and ComfyUI workflow execution. Sanitization: Absent. This surface is inherent to the intended creative use-case and is managed locally.
Audit Metadata