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