message-chunker
Security checks across static analysis, malware telemetry, and agentic risk
Overview
This instruction-only skill coherently tells the agent to split long outgoing messages, with minor review points around automatic multi-message sending and an unspecified failure queue.
This skill appears safe for its stated purpose of splitting long messages. Before installing, be aware that it may send one response as several messages and may queue failed chunks; avoid using it for highly sensitive content unless your OpenClaw environment gives you clear control over retries and retained failures.
Static analysis
No static analysis findings were reported for this release.
VirusTotal
VirusTotal findings are pending for this skill version.
Risk analysis
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 single long message may be posted as several messages, which could matter in public or sensitive chats.
The skill instructs the agent to automatically split a long response and send additional continuation messages. This matches the skill purpose, but it affects outgoing messaging behavior.
在回复长消息时，Agent会自动判断并分段 ... # 系统自动发送第2条
Use it when multi-part sending is desired, and review destination and content before asking the agent to send sensitive or public messages.
If a failed long message contains private information, parts of it could be retained in an unspecified queue.
The skill says failed chunks should be recorded to a failure queue. That is related to retry handling, but the artifacts do not define retention, storage location, or whether sensitive message content is excluded.
重试机制 - 分段后仍失败则记录到失败队列
Avoid sending highly sensitive content unless you understand how the host agent handles failed-message queues, or configure the workflow to avoid retaining failed chunks.