abuselpdb

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

• Third-party content exposure detected (high risk: 0.80). The skill's SKILL.md directs the agent to connect to the public AbuseIPDB API (abuseipdb.com) via Membrane and run actions such as "get-reports" and "get-blacklist" that ingest community/user-generated reports from the open web, which the agent is expected to read and use to make decisions (e.g., blocking), so untrusted third‑party content can influence behavior.