polygon

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

• Third-party content exposure detected (high risk: 0.80). The skill uses Membrane to run Polygon actions that fetch external public data (e.g., the "Get Ticker News" action listed in SKILL.md and general membrane action run patterns against the Polygon connector/polygon.io), so the agent will ingest untrusted third‑party content (news/articles) that could influence subsequent decisions.

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 — e.g. https://www.npmjs.com/package/@membranehq/cli or https://registry.npmjs.org/@membranehq/cli), which fetches and installs remote code that is executed at runtime to control actions/auth and is a required dependency.