open-design-preview
Pass
Audited by Gen Agent Trust Hub on Nov 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's workflow for identifying and previewing design artifacts creates an indirect prompt injection surface.
- Ingestion points: The agent is instructed to read '.artifact.json' files within the '.open-design/' directory to identify designs.
- Boundary markers: No explicit boundary markers or instructions are provided to distinguish between legitimate design data and potential malicious instructions embedded within the artifact files.
- Capability inventory: The skill utilizes the 'open_open_design_preview' tool to render content in a browser based on the ingested file paths.
- Sanitization: The instructions do not specify any sanitization or validation of the metadata within the JSON artifacts before the agent processes them.
Audit Metadata