Skillv1.0.0

ClawScan security

agent-communicator · ClawHub's context-aware review of the artifact, metadata, and declared behavior.

BenignApr 29, 2026, 10:07 AM

Verdict: benign
Confidence: high
Model: gpt-5-mini
Summary: The skill is an instruction-only template for inter-agent messaging; its requirements and instructions are coherent with that purpose and it does not request extra credentials, installs, or system access.
Guidance: This skill is an instruction-only set of message templates and patterns for coordinating agents and appears coherent and low-risk. Before installing, consider: (1) whether your agents will include any sensitive data in messages (the skill provides templates but doesn't sanitize content), (2) governance for autonomous agents that may forward or broadcast messages — ensure policies prevent accidental leakage, and (3) review how you wire this skill into agent workflows (it won't request credentials or install anything, but downstream agents or integrations you connect it to might). If you need more assurance, ask for a brief example of how it will be invoked in your environment and what data will be exchanged.

Purpose & Capability: okName/description describe inter-agent message patterns and the skill only supplies message formats, templates, patterns, and examples — all coherent with an agent-communicator purpose.
Instruction Scope: okSKILL.md contains templates, protocols, examples and logging/QA guidance but does not instruct the agent to read local files, call external endpoints, exfiltrate data, or access environment variables. References are to bundled example markdown only.
Install Mechanism: okNo install spec and no code files — instruction-only. Nothing will be written to disk or downloaded by an installer, which minimizes risk.
Credentials: okNo required environment variables, credentials, or config paths are declared. The templates do reference e.g. service URLs in examples, but the skill does not request secrets or unrelated credentials.
Persistence & Privilege: okalways is false and the skill is user-invocable; it does not request persistent system-level presence or modifications to other skills. Default autonomous invocation is allowed by platform but is not elevated here.