link-scraper

Warn

Audited by Snyk on Mar 1, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (high risk: 1.00). The skill explicitly fetches and scrapes arbitrary HTTP/HTTPS URLs (see fetch/extract in index.js and scrape.js) and SKILL.md instructs the agent to use it to read and summarize user-shared web pages, so untrusted third-party page content can directly influence the agent's summaries and subsequent actions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 1, 2026, 05:11 AM