visual-style

Pass

Audited by Gen Agent Trust Hub on Jun 20, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill stores aesthetic preferences in a dedicated local directory, following standard data management practices.
  • [EXTERNAL_DOWNLOADS]: The skill analyzes visual patterns from external websites using WebFetch as a primary feature. It does not download executable code or configuration from untrusted sources.
  • [PROMPT_INJECTION]: The skill processes untrusted web data which creates an indirect prompt injection surface. (1) Ingestion points: URLs scraped via WebFetch in SKILL.md. (2) Boundary markers: None. (3) Capability inventory: Writes to brand/creative-kit.md; no shell or network access. (4) Sanitization: None mentioned.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 20, 2026, 07:32 PM
Security Audit — agent-trust-hub — visual-style