Group Chat Response
PassAudited by ClawScan on May 1, 2026.
Overview
This instruction-only skill coherently limits when an agent replies in group chats and shows no evidence of code execution, credential use, data exfiltration, or hidden behavior.
This appears safe for its stated purpose. Before installing, understand that it may make the agent stay quiet in group chats unless directly named or clearly relevant, and verify any identity or persistent behavior configuration it relies on.
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.
The agent may not answer general group-chat requests unless the user clearly calls it or asks for a capability it has.
The skill changes the agent's stopping and response conditions so it may remain silent unless explicitly addressed.
只回应被叫到的自己，保持安静让对话有序进行。
Install this only if you want stricter group-chat turn-taking, and make sure users know they should address the agent directly when they need it.
If the agent identity or group-member context is wrong, the agent could answer at the wrong time or stay silent when expected.
The skill relies on persistent identity/context information to decide when to respond, so incorrect or manipulated identity context could affect behavior.
读取你的 IDENTITY.md，记住你的名字和身份
Keep identity and agent-roster files accurate and trusted, and review any persistent configuration changes before applying them.