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: 1.00). The skill's "Deep Research Phase" instructs the research-specialist to read 20–30+ sources including Stack Overflow, GitHub discussions, community forums, and technical blogs—public, user-generated/untrusted content that the agent is expected to ingest and interpret.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 16, 2026, 01:11 AM