matterport

Warn

Audited by Snyk on Apr 29, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (high risk: 0.70). This skill explicitly instructs the agent to connect to a Matterport account via the Membrane CLI (e.g., "membrane connect --connectorKey matterport") and to discover and run actions ("membrane action run ...", with results in the output field), which means the agent will fetch and read user-generated third-party Matterport content as part of its workflow and that content could influence subsequent tool use or decisions.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Apr 29, 2026, 04:52 PM
Issues
1