deep-research

Warn

Audited by Snyk on Mar 8, 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 required Research Workflow (Step 3 "Gather sources" and Step 4 "Extract insights") explicitly instructs the agent to collect and interpret evidence from public third‑party sources (e.g., engineering blogs, industry reports, product case studies), meaning untrusted user-generated/open web content will be ingested and can influence conclusions and recommended actions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 8, 2026, 02:54 PM
Security Audit — snyk — deep-research