Research
Warn
Audited by Snyk on Feb 28, 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 workflows (e.g., Workflows/ExtractAlpha.md using "fabric -y" for YouTube, Workflows/Retrieve.md and WebScraping.md using WebFetch/BrightData/Apify, and Standard/Extensive/ClaudeResearch workflows using WebSearch/WebFetch) explicitly fetch and ingest content from arbitrary public websites, YouTube, and search results — untrusted third‑party/user‑generated content that the agents are required to read and use to drive research decisions and follow-up actions.
Audit Metadata