requirement-analysis

Warn

Audited by Snyk on Feb 16, 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's Stage 3 "外部资源研究" explicitly calls for 网页搜索 (exa MCP → WebSearch) and context7 via "WebSearch + Grep + Read", meaning the agent will fetch and read public web and third-party documentation (potentially user-generated/untrusted) as part of its workflow.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 16, 2026, 02:39 AM