implementation-approach
Warn
Audited by Snyk on Mar 8, 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). The SKILL.md explicitly instructs "Research and Exploration: Tech stack examples (WebSearch), similar projects, OSS references, literature/blogs" and "Active WebSearch Use," which requires the agent to fetch and interpret open/public web content (e.g., blogs, OSS, web search results) that could contain untrusted, user-generated instructions influencing strategy decisions.
Audit Metadata