sd-decision-engine
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill operates entirely within the agent's conversational context, providing logic and structured templates for cinematographic decision-making. It does not utilize any external tools, network capabilities, or file system operations.
- [SAFE]: No obfuscation, hardcoded credentials, or remote code execution patterns were detected in the instructions or reference files.
- [SAFE]: While the skill ingests external content (scripts and outlines) from a controller agent, it lacks any exploitable capabilities (such as shell execution or network access) that could be leveraged for an indirect prompt injection attack.
Audit Metadata