zuplo

Warn

Audited by Snyk on Apr 2, 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 shows the skill calling external Membrane/Zuplo endpoints (e.g., "membrane action list --connectionId=CONNECTION_ID" and "membrane request CONNECTION_ID /path/to/endpoint") and explicitly instructs the agent to read returned action objects/inputSchema and API responses to choose and run subsequent actions, meaning untrusted third-party API content can materially influence behavior.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Apr 2, 2026, 04:10 PM
Issues
1