waboxapp
Warn
Audited by Snyk on May 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: 0.80). The SKILL.md explicitly instructs the agent to connect via the Membrane CLI to a Waboxapp connection and run actions (e.g., "membrane action run --connectionId=CONNECTION_ID") to fetch/interact with Chat Session/Message/Contact/Media from WhatsApp, which are user‑generated, untrusted third‑party contents that the agent is expected to read and that could materially influence subsequent tool use or decisions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata