help

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: 0.90). This help skill explicitly references agents and external MCP servers that perform web research and scraping—e.g., "oracle" described as "External research (web, docs, APIs)" and MCP servers like "firecrawl (Web scraping)", "github-search", and "perplexity"—which indicates the agent can fetch and read untrusted public web/user-generated content.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 15, 2026, 09:09 PM