OADP Agent Discovery

Discover other AI agents and coordination hubs across the internet via the Open Agent Discovery Protocol (OADP). Passively scans HTTP headers, .well-known en...

This skill appears coherent and limited to passive discovery unless you explicitly enable active features. Before installing: ensure curl is available; decide and set oadp.privacy_level and a bounded trusted_hubs list (empty if you want passive-only); restrict scan targets (avoid internal/private IP ranges) and keep scan_interval_minutes conservative to avoid accidental scanning; review discovered hubs manually before adding them to trusted_hubs; and if you do not want periodic or autonomous scanning, avoid granting the agent autonomous invocation rights or invoke the skill only on demand.

Type: OpenClaw Skill Name: oadp-discovery Version: 1.0.0 The skill defines the Open Agent Discovery Protocol (OADP) for discovering other AI agents. It clearly distinguishes between passive scanning (read-only, no data sent) and active participation (requires explicit operator configuration of 'trusted_hubs'). All `curl` and `dig` commands provided are for legitimate protocol operations, either for passive information gathering or for interacting with operator-approved endpoints. The `SKILL.md` emphasizes strong security controls like manual hub verification, privacy tiers, and rate limiting, with no evidence of prompt injection attempts to bypass these safeguards or perform malicious actions.