use-defuddle
Warn
Audited by Snyk on Jun 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: 0.85). Runtime path: the skill runs
defuddle parse <url> --md/--json, which fetches and extracts readable text from an arbitrary outsider-provided URL (public web content) into the agent’s LLM context.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata