jetbrains-marketplace

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

• Third-party content exposure detected (low risk: 0.10). The skill reads user reviews and extension data from JetBrains Marketplace, which contains outsider-authored content.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (medium risk: 0.30). The skill instructs the installation and execution of an external package from an npm registry locator (@membranehq/cli), which constitutes an operational dependency with unverifiable third-party registry provenance.