OADP Agent Discovery
Analysis
The skill is coherent with its stated purpose of discovering OADP agent hubs, with disclosed network scanning and configuration-gated active participation.
Findings (4)
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
Checks for instructions or behavior that redirect the agent, misuse tools, execute unexpected code, cascade across systems, exploit user trust, or continue outside the intended task.
Passively scans HTTP headers, .well-known endpoints, markdown, HTML, robots.txt, and DNS for agent hub signals.
The skill gives the agent a network discovery workflow using public web and DNS lookups. This is central to the stated purpose, but it is still external scanning behavior.
Passive scanning sends zero data. You're reading public web content — no different from fetching a robots.txt or checking HTTP headers.
This appears intended to mean no agent profile data is intentionally shared, but passive HTTP/DNS requests still reveal ordinary network metadata such as source IP and request headers.
Checks for exposed credentials, poisoned memory or context, unclear communication boundaries, or sensitive data that could leave the user's control.
Active ping | Introduce yourself to a discovered hub ... Registration | Join a hub as a member ... Federation | Report discovered hubs to your trusted hubs
The skill can communicate with agent hubs and share agent or discovery information, but the artifact says these actions require explicit trusted-hub or federation configuration.
Log discovered hubs with a `verified: false` flag. Only set `verified: true` after the operator reviews the `.well-known` endpoint and adds the hub to `trusted_hubs`.
The skill maintains discovery and trust state that can influence future hub interactions. The artifact includes safeguards such as unverified flags and manual verification.