search-api

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

• Third-party content exposure detected (low risk: 0.10). The required runtime workflow (“Search API” skill) only follows first-party documentation to run Google’s Custom Search API via Membrane using explicit developer-specified endpoints/queries, and there is no indication that outsider-authored free text is ingested into a monitored feed/queue without selecting a specific item first.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill repeatedly invokes "npx @membranehq/cli@latest" (e.g., lines showing npx commands), which fetches and executes remote npm package code at runtime and is relied upon as a required dependency.