wuf

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

• Third-party content exposure detected (high risk: 0.70). The SKILL.md explicitly instructs the agent to use the Membrane CLI to list and run actions against Wuf (e.g., "membrane action list" and "membrane action run") to retrieve Wuf data such as pet and vet profiles — third-party, user-generated content that the agent will read and could materially influence subsequent actions.

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

• Potentially malicious external URL detected (high risk: 0.80). The skill invokes and depends on the Membrane CLI fetched and executed from the npm registry (commands shown: "npm install -g @membranehq/cli@latest" and "npx @membranehq/cli@latest"), which downloads and runs remote code at runtime, so it is a required external runtime dependency that executes remote code.