geometric-elements
Warn
Audited by Snyk on Feb 15, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.80). The skill's "From Reference Image" section in SKILL.md states that users can send reference images which Claude analyzes and recreates, meaning the agent ingests and interprets untrusted user-provided content as part of its workflow.
Audit Metadata