deep-research
Warn
Audited by Snyk on Feb 16, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). The skill explicitly performs WebSearch/WebFetch and GitHub issue/forum searches (e.g., "JUCE forum search via WebSearch" and "GitHub issue search (juce-framework/JUCE)") and synthesizes those public, user-generated sources as part of its research workflow, exposing the agent to untrusted third-party content.
Audit Metadata