gemini-cli

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly states Gemini CLI has "built-in Google Search grounding" and "can ... fetch web content" and instructs delegating work to gemini and using its captured output to continue the agent's workflow, which means untrusted public web content could be ingested and influence subsequent actions.