shodan

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly fetches and summarizes data from the public Shodan network database (see SKILL.md examples like "x shodan internetdb 8.8.8.8" and "x shodan :: '...'" which show the agent ingesting live, untrusted, third-party host data), so those external results can be read and used to drive AI summaries and follow-up actions.