research-strategy

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). This skill explicitly instructs the agent to gather and interpret public community sources—see "Source Prioritization" (Stack Overflow, GitHub issues/PRs, technical blogs) and "Gather Raw Information"—which are untrusted user-generated third-party contents the agent would read and could carry indirect prompt injection.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 16, 2026, 12:26 PM