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