content-bridge

Warn

Audited by Snyk on Mar 7, 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 and INTERFACE.md explicitly route and ingest arbitrary public third‑party content (e.g., "任意网页", mp.weixin.qq.com via MCP, YouTube/youtu.be, bilibili, and WebSearch) and then upload and use that content as inputs to NotebookLM to drive generation, so untrusted/user‑generated content is read and can materially influence subsequent tool actions.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

  • Potentially malicious external URL detected (high risk: 0.80). The skill installer and runtime require cloning and running the MCP server from GitHub (git clone https://github.com/Bwkyd/wexin-read-mcp.git then running its src/server.py), which fetches remote code that is executed and is a required dependency for Weixin extraction, so this external URL constitutes a runtime-executed remote-code dependency.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 7, 2026, 02:52 AM