A2A Agent Lookup — Verify Any AI Agent
PassAudited by ClawScan on May 1, 2026.
Overview
This instruction-only skill looks coherent and low-risk, but users should treat its third-party reputation claims and agent endpoint listings as advisory rather than definitive.
This skill appears safe to install as an instruction-only lookup helper. Be aware that it depends on RNWY’s registry and trust scores, so verify high-stakes agents or endpoints independently before sharing private information, sending funds, or authorizing actions.
Findings (2)
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.
A user or agent may place too much trust in the registry’s 'verified' or 'trusted' labels when deciding whether to interact with another AI agent.
The skill uses strong reputation and verification language for a third-party registry. This is aligned with the lookup purpose, but users should understand it is a registry claim rather than an independent guarantee.
The only registry with verified identity AND live A2A endpoints at scale.
Use the lookup results as one input, and independently verify important agents, endpoints, and transaction details before sharing sensitive data or hiring/transacting.
If a user follows an endpoint from the registry, they may communicate with an external agent or service whose behavior is outside this skill’s control.
The skill surfaces third-party A2A and service endpoints for other agents. That is the intended function, but those endpoints are external trust boundaries.
Returns the agent's full A2A card: name, description, capabilities, services, endpoints, on-chain registration, and RNWY trust data.
Before interacting with a listed endpoint, confirm it matches the intended agent and avoid sending credentials, private data, or irreversible instructions unless you trust that external agent.