stitch-ui-design-spec-generator
Pass
Audited by Gen Agent Trust Hub on Apr 2, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill's primary function is to interpret design requests and categorize them into a fixed JSON schema. The logic rules (Analyze Tone, Determine Device, Determine Mode) are focused entirely on creative direction and do not involve suspicious command execution or privilege escalation.
- [SAFE]: No obfuscated code, hidden URLs, or hardcoded credentials were found in the skill definitions or usage examples. All external references point to internal documentation or common licenses.
- [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection as it ingests untrusted data from product requirement documents (PRD) and user requests to populate JSON fields. While this is a vulnerability surface, the risk is currently limited to the styling metadata and does not present a path for high-severity exploitation in the context of this skill.
- Ingestion points: User-supplied natural language requests and contents of product requirement documents (PRD) accessed via project file paths.
- Boundary markers: The instructions do not define delimiters or warnings to isolate untrusted input from the instruction set.
- Capability inventory: The skill utilizes 'Read' and 'Write' tools to handle project files and passes its output to the 'stitch-ui-prompt-architect' for prompt assembly.
- Sanitization: No input sanitization or validation is implemented for the extracted text before it is inserted into the output specification JSON.
Audit Metadata