researching-ai-news

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: 1.00). This skill explicitly uses Perplexity MCP tools (mcp__perplexity__perplexity_search and mcp__perplexity__perplexity_research) to fetch titles, URLs, snippets and citations from public web pages and news sources, so it ingests untrusted third‑party content as part of its workflow.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 15, 2026, 08:42 PM