defuddle
Warn
Audited by Snyk on Jul 16, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.85). The required workflow runs
defuddle parse <url> --md, which fetches and converts public web page content into markdown that is then ingested into the agent context, creating an indirect prompt-injection path from outsider-authored web text.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata