od-prototype-card-xiaohongshu
Pass
Audited by Gen Agent Trust Hub on Oct 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: No security threats detected. The skill follows established patterns for template-based design generation and artifact registration.
- [INDIRECT_PROMPT_INJECTION]: The skill accepts user input via the $ARGUMENTS variable, creating a surface for potential injection into the design brief. 1. Ingestion points: $ARGUMENTS in SKILL.md. 2. Boundary markers: Absent. 3. Capability inventory: MCP tool calls (prepare_open_design_brief) and local file-editing tools. 4. Sanitization: Absent.
Audit Metadata