writing-assistant

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

• Third-party content exposure detected (high risk: 0.70). The skill's required Proofreading workflow explicitly includes "Step 4: Source Verification" and the references/source-verification.md directs the agent to search for and cite external public sources (with links and footnotes), meaning the agent is expected to fetch and interpret open web content that could be untrusted.