defuddle
Warn
Audited by Snyk on Jul 24, 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). SKILL.md instructs running
defuddle parse <url> --md, which at runtime fetches outsider-authored public web page content via the CLI and ingests it into the agent context as readable markdown, creating indirect prompt-injection risk.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata