sd-storyboard-engine
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: Extensive review of the skill's instructions and reference files found no evidence of malicious intent, unauthorized data access, or external communication. The skill operates within a closed environment using local assets.
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied script data, creating a potential surface for indirect prompt injection. 1. Ingestion points: Received original script or novel text. 2. Boundary markers: Uses structured output formats but lacks explicit input filtering. 3. Capability inventory: Outputting detailed shot lists and prompt engineering for image assets. 4. Sanitization: Not explicitly implemented for untrusted text inputs. This surface is considered a low risk inherent to the skill's design.
- [COMMAND_EXECUTION]: Mention of validation scripts like validate_prompt.py and check_package.py pertains to internal consistency checks within the project's own file structure and does not represent an external or unauthorized command execution risk.
Audit Metadata