remove-model-cliche

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

• Third-party content exposure detected (high risk: 1.00). The skill's required workflow step 2 explicitly instructs the agent to perform a web_search of the current internet and ingest found web content to identify and replace "model" clichés (i.e., fetching open/public third‑party pages), so untrusted external content can directly influence edits and subsequent actions.