claude-agent-sdk

Warn

Audited by Snyk on Apr 22, 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 exposes Claude agents to arbitrary public web content via built-in tools "WebSearch" and "WebFetch" (listed in SKILL.md) and shows examples of custom tools and MCP HTTP/SSE servers fetching arbitrary URLs (references/custom-tools.md and MCP server examples), and those fetched results are fed back into the agent loop and used to drive subsequent tool calls and decisions.

Issues (1)

W011
MEDIUM

Third-party content exposure detected (indirect prompt injection risk).

Audit Metadata
Risk Level
MEDIUM
Analyzed
Apr 22, 2026, 12:35 PM
Issues
1
Security Audit — snyk — claude-agent-sdk