defuddle
Warn
Audited by Snyk on Feb 15, 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 explicitly runs Defuddle on arbitrary user-provided URLs to extract markdown from web pages (online documentation, articles, blog posts), so the agent will ingest untrusted public web content that could contain indirect prompt-injection.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.90). The skill runs the Defuddle CLI at runtime using "defuddle parse " to fetch arbitrary user-provided web pages (the placeholder ), and the extracted markdown is intended to be injected into the agent's context so the fetched content can directly control prompts or instructions.
Audit Metadata