canvas-design

Pass

Audited by Gen Agent Trust Hub on Sep 14, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill possesses a data ingestion surface by processing user instructions to create custom design philosophies.
  • Ingestion points: User-provided textual input describing the theme or request in SKILL.md.
  • Boundary markers: Absent.
  • Capability inventory: None; no executable scripts, tool calls, or code execution layers are distributed with this skill.
  • Sanitization: Absent.
  • Context: Because the skill lacks active capabilities or code components, any processed user instructions present no behavioral risk to the system.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 14, 2026, 11:00 PM
Security Audit — agent-trust-hub — canvas-design