stitch-ui-design-spec-generator
Pass
Audited by Gen Agent Trust Hub on Aug 19, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection by processing external user-provided data.
- Ingestion points: User-provided PRD documents or file paths are ingested into the agent context in SKILL.md and examples/usage.md.
- Boundary markers: There are no explicit delimiters or instructions to ignore embedded commands within the processed PRD content.
- Capability inventory: The skill uses Read and Write tools, allowing it to interact with the file system based on user-provided paths.
- Sanitization: There is no evidence of input validation or sanitization for the data extracted from PRDs.
- [SAFE]: The skill references documentation and workflow guides from the vendor's official GitHub repository.
Audit Metadata