desearch-crawl

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: 1.00). The skill explicitly fetches and returns content from arbitrary public web pages — SKILL.md "Crawl Webpage By Desearch: Extract content from any webpage URL" and scripts/desearch.py (cmd_crawl -> /web/crawl using the user-supplied url) show the agent ingests untrusted third-party page content that could contain instructions influencing behavior.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 10, 2026, 03:07 PM