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
Risk Level
MEDIUM
Analyzed
Mar 8, 2026, 07:02 PM