stitch-ui-design-spec-generator

Pass

Audited by Gen Agent Trust Hub on Apr 6, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: Indirect prompt injection vulnerability surface detected in the processing of PRD documents.
  • Ingestion points: Reads Product Requirement Documents (PRDs) from provided file paths or user-pasted content as specified in SKILL.md and examples/usage.md.
  • Boundary markers: Missing explicit delimiters or instructions to ignore commands embedded within the PRD content.
  • Capability inventory: Uses Read, Write, and stitch*:* tools across its operations, which could be abused if an injected instruction is followed by the agent.
  • Sanitization: Content from external files is processed and interpolated into design logic without validation or escaping mechanisms.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 6, 2026, 10:43 AM