Multi-Agent Chat Protocol
ReviewAudited by ClawScan on May 10, 2026.
Overview
Prompt-injection indicators were detected in the submitted artifacts (unicode-control-chars); human review is required before treating this skill as clean.
This appears safe to install as an instruction-only coordination aid. Be aware that it may make your agent stay silent, answer briefly, or pause a conversation in multi-bot Discord channels by design. ClawScan detected prompt-injection indicators (unicode-control-chars), so this skill requires review even though the model response was benign.
Findings (1)
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.
In the intended multi-bot Discord setting, the agent may shorten responses, refuse to answer questions directed at other agents, or stop bot-to-bot exchanges until a human intervenes.
The skill intentionally makes its conversation rules authoritative for the agent, which can affect normal response behavior.
Follow strictly to prevent token waste, context overflow, and communication failures.
Use this skill only for multi-agent Discord conversations where those turn-taking and silence rules are desired.