NYC

research-lookup

Warn

Audited by Snyk on Feb 16, 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 explicitly queries third-party sources via OpenRouter/Perplexity Sonar (see "Technical Integration" mentioning OpenRouter and Sonar models) and also uses WebSearch for news, blogs, and non-scholarly sites, so it fetches and ingests open/public third‑party content that the agent reads as part of its workflow.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 16, 2026, 03:08 AM