NYC

research-lookup

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: 0.80). The skill calls OpenRouter / Perplexity Sonar models to perform online academic/web searches and returns model-generated content and source links (see research_lookup.py and README usage of "academic/scholarly search mode" and lookup.py formatting of "response" and "citations"), so it ingests and displays third‑party public content that could carry indirect prompt injections.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 15, 2026, 08:59 PM