MOA-Debate

Run an Oxford Union–style multi-agent debate on any motion using Mixture of Agents architecture

This skill appears coherent for running simulated Oxford‑style debates: it contains role system prompts, round sequencing, and structured output formats but requests no credentials or installs. The main thing to watch for is prompt‑injection risk: the skill relies on many explicit system prompts and strict 'return only' instructions which are normal here but could be used to override model behavior if the hosting platform does not enforce prompt isolation. Before installing: (1) confirm the platform prevents skill prompts from accessing or leaking sensitive agent/system context, (2) avoid providing any secret or private material as debate motions or examples, and (3) run a few test debates with non‑sensitive motions to verify outputs match expectations. If you need higher assurance, ask the platform vendor whether skill system prompts are sandboxed and whether skills can access other skills' credentials or agent internals.

Type: OpenClaw Skill Name: mixtureofagents-debate Version: 1.0.0 The skill is classified as suspicious due to a significant prompt injection vulnerability. The user-provided 'motion' is directly embedded into numerous LLM prompts within SKILL.md without any apparent sanitization or separation. This allows a malicious user to craft a motion containing arbitrary instructions, potentially manipulating the agent's behavior beyond its intended purpose, such as attempting to extract sensitive information or execute unauthorized actions via the underlying LLM.