adk-integrations

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

• Third-party content exposure detected (high risk: 0.90). The skill's SKILL.md explicitly directs the agent to run live CLI commands (adk search, adk info) via the Bash tool and the references (references/common-integrations.md and lifecycle.md) document the browser integration's webSearch/browsePages scraping actions that ingest public web content the agent is expected to read and act on, so untrusted third‑party pages can materially influence subsequent actions.