anti-ai-slop-design
Pass
Audited by Gen Agent Trust Hub on Sep 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted external data such as screenshots, mockups, and design briefs.
- Ingestion points: The workflow specifies inspecting supplied screenshots, mockups, or project context (SKILL.md).
- Boundary markers: There are no defined boundary markers or instructions to ignore instructions potentially embedded within user-provided design artifacts.
- Capability inventory: The skill has the capability to edit code, generate images, and use other tools for execution (SKILL.md).
- Sanitization: The instructions do not specify sanitization or validation of the content within the input artifacts.
Audit Metadata