research

Warn

Audited by Snyk on Mar 6, 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). This skill's required Research Workflow and Platform-Specific Research Tools explicitly instruct the agent to use web search and platform analytics to find and ingest public third‑party content (e.g., "use web search" and "Find 5-8 top-performing pieces... link") and to read/interpret those items to drive competitor analysis, gap ratings, and recommended angles, which could allow indirect prompt injection from untrusted public sources.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 6, 2026, 01:32 AM