holobuilder

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). The SKILL.md instructs the agent to use the Membrane CLI to connect to HoloBuilder (a third-party platform hosting user-generated 360° photos, annotations, and project data) and explicitly shows workflows to list and run actions (membrane action list / membrane action run) that fetch and return that content for the agent to read and act on, so untrusted third-party content can influence behavior.

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

  • Potentially malicious external URL detected (high risk: 0.70). The skill requires installing and running the Membrane CLI via "npm install -g @membranehq/cli@latest" (fetched from the npm registry, e.g. https://registry.npmjs.org/@membranehq/cli), which downloads and executes remote code at runtime and is a required dependency for the skill.

Issues (2)

W011
MEDIUM

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

W012
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Apr 29, 2026, 10:37 PM
Issues
2
Security Audit — snyk — holobuilder