research-lookup
Warn
Audited by Snyk on Mar 24, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). This skill autonomously queries web-grounded providers (Perplexity Sonar via OpenRouter in research_lookup.py / lookup.py / scripts/research_lookup.py and Gemini Deep Research in gemini_research.py), ingests public web and academic sources (URLs, snippets, citations) and uses them in its core workflow and outputs, so untrusted third-party content can materially influence model behavior and downstream decisions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata