mokeaigc-v9
Pass
Audited by Gen Agent Trust Hub on Oct 5, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides a robust framework for cinematic world-building without any detected security risks. It focus on prompt generation and continuity management.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted user input (a 'creative spark' or reference image) to generate downstream prompts for image generators.
- Ingestion points: User-provided text or image references in
SKILL.md(Workflow Step 1). - Boundary markers: The skill instructs the agent to separate 'observed' reference evidence from 'creative extension', which acts as a structural boundary.
- Capability inventory: The skill's primary capability is text generation for external image AI tools; it does not have file-write, network-send, or code-execution capabilities.
- Sanitization: None explicitly defined, but the structured 'Aspect Matrix' and 'Continuity Bible' logic naturally constrain the output space. This represents a standard surface for LLM interaction and does not warrant a non-safe verdict.
Audit Metadata