yuki

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

• Third-party content exposure detected (high risk: 0.90). The skill instructs the agent to fetch and operate on Yuki data via Membrane (e.g., "membrane action run ..." and "membrane request CONNECTION_ID /path/to/endpoint" in SKILL.md), which can include customer/user-generated content from a third-party SaaS and thus could inject instructions that influence subsequent agent actions.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill requires installing and running the external Membrane CLI (npm install -g @membranehq/cli), which fetches and executes remote code from the npm registry (e.g., https://registry.npmjs.org/@membranehq/cli) at runtime and is a required dependency.