google-docs

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly instructs the agent to fetch and read Google Docs content via the Google Docs API (see "Get Document Content" and "Extract Plain Text"), which ingests user-generated/untrusted document content that the skill then uses to compute indexes and drive batchUpdate operations—allowing third-party content to materially influence subsequent actions.