llm-price-scraper

Warn

Audited by Snyk on Mar 10, 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 workflow and README explicitly instruct the agent to open and scrape arbitrary provider URLs using agent-browser (e.g., "agent-browser open " and "使用 llm-price-scraper 获取 https://example.com/pricing 的数据"), so the agent ingests open/public third‑party web pages whose content directly guides navigation and extraction and could therefore influence its actions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 10, 2026, 04:51 AM