rtk
Warn
Audited by Snyk on Apr 18, 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). Yes — SKILL.md explicitly lists network commands like "rtk curl " and "rtk wget " (Network section) which fetch and compact HTTP responses from arbitrary public URLs, meaning the agent will read and act on untrusted third‑party web content.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata