onsh

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

• Third-party content exposure detected (high risk: 0.70). The skill explicitly instructs the agent to search and read the public xon.sh website (e.g., "Search xon.sh for syntax, alias, or Python-integration tips" and the example "x onsh : alias"), so it will fetch and interpret third-party web documentation that can influence subsequent actions.