uscreen

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

• Third-party content exposure detected (high risk: 0.70). The skill's SKILL.md instructs the agent to query and proxy requests to the third-party Uscreen API (e.g., "membrane action list", "membrane action run", and "membrane request CONNECTION_ID /path/to/endpoint") and explicitly lists user-generated resources such as Blog Post and Comment, so the agent will fetch and act on untrusted third-party content from Uscreen.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill relies on the Membrane CLI and shows runtime commands that fetch and execute remote packages (e.g., "npm install -g @membranehq/cli" and "npx @membranehq/cli@latest", which pull code from the npm registry such as https://registry.npmjs.org/@membranehq/cli), so remote code is fetched/executed at runtime and is required for the skill.