devdocs-requirements

Warn

Audited by Snyk on Mar 11, 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). Yes — the skill's "背景信息模式" explicitly instructs the agent to fetch and summarize arbitrary URL links using WebFetch (e.g., "URL 链接 | 使用 WebFetch 提取摘要" and "背景信息模式" workflow and constraints), so it will ingest untrusted third‑party webpages and integrate their content into decision-making and document updates.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 11, 2026, 06:08 AM