mermaid

Warn

Audited by Snyk on Apr 29, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (high risk: 0.70). The SKILL.md "Resilient Workflow" explicitly lists an error-recovery step ending in "→ WebSearch", which indicates the required workflow expects the agent to consult open/public web content (third‑party, untrusted) as part of diagnosing/rendering diagrams and therefore could allow indirect prompt injection.

Issues (1)

W011
MEDIUM

Third-party content exposure detected (indirect prompt injection risk).

Audit Metadata
Risk Level
MEDIUM
Analyzed
Apr 29, 2026, 12:28 PM
Issues
1
Security Audit — snyk — mermaid