defuddle
Warn
Audited by Snyk on Mar 8, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 1.00). SKILL.md explicitly instructs the agent to fetch arbitrary public webpages via the defuddle.md service (e.g., defuddle.md/x.com/username/status/...), causing the agent to ingest untrusted, user-generated web content that it will read and act on, which can enable 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 calls the external service "defuddle.md/" at runtime (via curl) to fetch arbitrary Markdown which is injected into the agent's context, so remote content from defuddle.md can directly control prompts/instructions.
Audit Metadata