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: 0.80). The skill's Phase 2 "Gather" step and Source Priority explicitly direct the agent to collect and read open/public user-generated content (community discussions, Stack Overflow, GitHub issues, conference posts/case studies and other public websites), so the agent would ingest untrusted third-party material that could enable indirect prompt injection.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 16, 2026, 07:37 PM