stitch-ui-design-spec-generator

Pass

Audited by Gen Agent Trust Hub on Jun 23, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns or high-risk security issues were detected in the instructions or example usage.
  • [PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection because it ingests untrusted data from user requests and external PRD documents. However, the potential impact is low as the skill lacks network access and its toolset is restricted to design-related tasks.
  • Ingestion points: User prompts and PRD files processed in SKILL.md and examples/usage.md.
  • Boundary markers: None identified; the skill does not use delimiters to isolate external document content from its internal instructions.
  • Capability inventory: Restricted to Read, Write, and platform-specific stitch tools as specified in the YAML frontmatter.
  • Sanitization: No explicit validation or filtering logic is present for external inputs.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 23, 2026, 04:04 PM
Security Audit — agent-trust-hub — stitch-ui-design-spec-generator