Latest release: v1.0.0Download zip
Capabilities
Compatibility
Security Scan
OpenClaw
Benign
medium confidencePurpose & Capability
The manifest, package metadata, and visible skill files consistently describe an instruction/reference skill for A2A multi-agent protocol development, not a runtime integration that acts on accounts or local data.
Instruction Scope
The skill repeatedly tells the agent to fetch or search current official documentation before writing code. This is purpose-aligned for an evolving protocol, but users should expect external web access when the skill is used for implementation help.
Install Mechanism
The registry says there is no install spec and no required binaries, environment variables, or credentials. The only provided script is a local secret-warning helper and is not shown as auto-installed or auto-run by the provided manifest.
Credentials
The skill discusses A2A networking, authentication, push notifications, and MCP bridges as development guidance. These are proportional to the stated purpose, but generated implementations may move task data between agents and services.
Persistence & Privilege
No provided artifact shows background persistence, self-propagation, privileged installation, protected-path writes, credential collection, or autonomous mutation of user systems.
Assessment
This appears safe to install as an instruction-only reference skill. Before using it to generate production code, review any web-fetched sources, keep credentials out of code, and explicitly decide which external agents, MCP tools, and callback URLs may receive your data. Some listed files were omitted or truncated in the supplied review context, so inspect the complete package if you need maximum assurance.