ai-app

Warn

Audited by Snyk on Mar 7, 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). The skill explicitly includes web-search functionality that ingests public web content (e.g., references/chatbot.md "Web Search Chatbot" using perplexity('sonar-pro') and rendering source URLs, and references/agent-dashboard.md's searchWeb tool), so the agent is expected to fetch and interpret untrusted third‑party webpages/sources as part of its workflow.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 7, 2026, 01:15 AM