agent-sdk-builder
Warn
Audited by Snyk on May 10, 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.md explicitly exposes WebSearch/WebFetch as built-in tools and shows examples (e.g., the "Built-in Tools" table and the "Multi-Agent Research Pipeline" example) where the agent performs web searches and fetches web pages, meaning it will read untrusted public web content that can influence its tool use and decisions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata