defuddle
Warn
Audited by Snyk on Mar 3, 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 explicitly instructs using "defuddle parse " to fetch and extract content from arbitrary web pages (public third-party sites), so untrusted user-generated web content would be ingested and could influence the agent's subsequent interpretation or actions.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 1.00). The skill runs the Defuddle CLI at runtime (e.g.,
defuddle parse <url> --md) to fetch arbitrary user-supplied webpages (the<url>passed to defuddle) and extract content that would be injected into agent context, so remote content can directly control prompts.
Audit Metadata