kickofflabs

Warn

Audited by Snyk on Apr 22, 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 use Membrane actions and proxy requests to fetch KickoffLabs data (e.g., "Get Lead", "List Campaign Actions", and the "membrane request" proxy) which are third‑party, user-generated/untrusted campaign/lead contents that the agent is expected to read and that can directly influence subsequent actions like tagging, blocking, or running additional requests.

Issues (1)

W011
MEDIUM

Third-party content exposure detected (indirect prompt injection risk).

Audit Metadata
Risk Level
MEDIUM
Analyzed
Apr 22, 2026, 07:40 AM
Issues
1