hivebrite

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

• Third-party content exposure detected (high risk: 0.70). This skill uses the Membrane CLI to connect to Hivebrite and run actions that read member-generated Hivebrite content (e.g., Articles, Messages, Events) — i.e., untrusted third-party/user-generated data the agent will ingest and act on as shown in the "Use when the user wants to interact with Hivebrite data" and action run/list examples in SKILL.md.

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

• Potentially malicious external URL detected (high risk: 0.80). The skill requires installing and running the Membrane CLI (npm install -g @membranehq/cli@latest and npx @membranehq/cli@latest), which fetches and executes remote code from the npm registry at runtime and is presented as a required dependency for the skill.