design-craft
Pass
Audited by Gen Agent Trust Hub on Oct 6, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill was analyzed for all 11 threat categories, and no malicious patterns, prompt injections, or data exfiltration attempts were detected. The content consists of legitimate design guidelines distilled from industry experts.- [NO_CODE]: The skill is composed entirely of Markdown documentation and instructions; it does not include any scripts, dependencies, or executable binaries.- [INDIRECT_PROMPT_INJECTION]: The skill possesses a vulnerability surface for indirect prompt injection as it is explicitly designed to analyze external URLs and screenshots provided by users during 'Review mode'.
- Ingestion points: External data enters the agent context through URLs and mockups as specified in
references/design-review-rubric.md. - Boundary markers: The instructions do not define specific delimiters or security warnings to the agent regarding the content found within those external sources.
- Capability inventory: The skill's capabilities are limited to generating design feedback and text-based UI suggestions; it does not have access to tools that would allow for file system modification, command execution, or network exfiltration.
- Sanitization: There is no sanitization or pre-processing of external content described in the workflow.
Audit Metadata