skill-browser-crawl

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: 0.90). This skill (see SKILL.md and scripts/basic_crawl.py and scripts/deep_crawl.py) explicitly fetches and ingests arbitrary public web pages provided as URLs, extracts their Markdown and links, and uses that extracted content/links to drive recursive crawling, so untrusted third‑party content can directly influence the agent's next actions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 1, 2026, 07:47 PM