creating-claude-agents
Warn
Audited by Snyk on Apr 4, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.80). This skill explicitly lists and auto-approves WebFetch/WebSearch as tools and describes agents using them for "research" and "documentation gathering" (see "Tool Configuration" / "Available Tools" and "Permission Mode" / "Auto Mode" / "Auto-approved" in SKILL.md and resources/agent-architecture.md), so the agent will fetch and interpret arbitrary public web content that could carry untrusted instructions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata