scrapingant

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly integrates ScrapingAnt (a web-scraping API) and instructs the agent to create and retrieve "Scraping Task" results via Membrane CLI (see SKILL.md sections "ScrapingAnt is a web scraping API..." and "Scraping Task" / "Running actions"), which means the agent will ingest arbitrary public website content that could contain user-generated or untrusted instructions affecting subsequent actions.

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

• Potentially malicious external URL detected (high risk: 0.80). The skill explicitly requires installing and running the Membrane CLI via "npm install -g @membranehq/cli@latest", which fetches and executes remote code at runtime and is relied upon to discover and run actions against external services, so it is a runtime external dependency that can execute code.