deep-research
Warn
Audited by Snyk on Feb 15, 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 Source Strategy and Information Gathering steps explicitly call for WebFetch/WebSearch and reading technical blogs, discussion forums, and GitHub repositories (Phase 2 / Step 4), meaning the agent will fetch and interpret open/public, user-generated third-party content that could carry indirect prompt-injection.
Audit Metadata