filestack

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

• Third-party content exposure detected (high risk: 0.70). The skill instructs the agent to connect to a third-party Filestack account via the Membrane connector and run actions that read "File Content" and other user-generated file data (see SKILL.md "Use when the user wants to interact with FileStack data" and the Files / File Content sections), so untrusted third-party content will be ingested and can influence subsequent actions.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill instructs running the Membrane CLI at runtime (e.g., "npx @membranehq/cli@latest" / https://www.npmjs.com/package/@membranehq/cli), which fetches and executes remote code and is a required dependency for the skill's operation.