agentic-research-workflow
Warn
Audited by Snyk on Oct 8, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (low risk: 0.10). The skill implements a research agent workflow that calls web search and document search APIs like Tavily, arXiv, and Wikipedia, allowing the LLM to process potentially untrusted external web content via active searching.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata