reviewflowz

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly instructs the agent to connect to Reviewflowz via the Membrane CLI and run/list actions (e.g., "membrane action list/run --connectionId=CONNECTION_ID") to fetch reviews, comments and user data from the Reviewflowz platform — user-generated third‑party content the agent is expected to read and that could 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 requires running remote packages (e.g., "npx @membranehq/cli@latest" and "npm install -g @membranehq/cli@latest"), which fetch and execute code from the npm registry at runtime and are relied on for the skill to operate.