basin

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

• Third-party content exposure detected (high risk: 0.90). This skill's SKILL.md instructs the agent to use the Membrane CLI to run Basin actions (e.g., list-submissions, get-submission via membrane action run) which fetch user-generated form submissions from a third-party service (Basin) that the agent is expected to read and could influence subsequent actions.

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 (fetched via "npm install -g @membranehq/cli@latest"), which downloads and executes remote code that the skill relies on at runtime.