v1.0.0

Debate Arena

BenignClawScan verdict for this skill. Analyzed May 1, 2026, 7:46 AM.

Analysis

This skill appears to run the advertised debate workflow, with expected local archiving and multi-agent coordination that users should understand before use.

GuidanceBefore installing, confirm you are comfortable with a user-started debate that can auto-advance rounds, send messages through configured role agents/accounts, and store debate state and archives under `~/.openclaw/debate-arena/`. Avoid sensitive debate content unless you trust the configured agents and the local storage location.

Findings (5)

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.

Abnormal behavior control

Checks for instructions or behavior that redirect the agent, misuse tools, execute unexpected code, cascade across systems, exploit user trust, or continue outside the intended task.

Tool Misuse and Exploitation

SeverityLowConfidenceHighStatusNote

SKILL.md

自动推动轮次：`autonext=true` 默认开启 ... `debate start`：启动辩论 ... `debate stop`：强制结束

After an explicit start, the debate can advance through turns automatically, but the behavior is disclosed and bounded by the configured debate rounds and stop command.

User impactOnce started, the skill may continue prompting configured debate agents without asking for approval before every round.

RecommendationCheck the configured participants and round count before starting; set `debate set autonext false` if you want to approve each round manually.

Agentic Supply Chain Vulnerabilities

SeverityInfoConfidenceMediumStatusNote

metadata

Source: unknown; Homepage: none

The package provenance is limited, although the artifacts do not show a remote installer, package dependency, or hidden helper being fetched.

User impactUsers have less external provenance information to rely on when deciding whether to trust the skill.

RecommendationReview the included files and install only if you trust the publisher or the local artifact contents.

Permission boundary

Checks whether tool use, credentials, dependencies, identity, account access, or inter-agent boundaries are broader than the stated purpose.

Identity and Privilege Abuse

SeverityInfoConfidenceHighStatusNote

SKILL.md

`debate set <pros|cons|judge>.accountId <id>`：指定发送账号

The skill allows a user to bind role agents to a sending account identifier, which is relevant delegated identity handling, though no credential storage or token use is shown.

User impactDebate messages may be sent using the account identity configured for a role.

RecommendationOnly configure account IDs you intend the debate roles to use, and verify the account choice before starting public or group debates.

Sensitive data protection

Checks for exposed credentials, poisoned memory or context, unclear communication boundaries, or sensitive data that could leave the user's control.

Memory and Context Poisoning

SeverityLowConfidenceHighStatusNote

SKILL.md

`debate set prompt <补充要求>` ... `debate conf`：保存为默认配置 ... Default config: `~/.openclaw/debate-arena/default-config.json`; State: `~/.openclaw/debate-arena/debate-state.json`; Archive dir: `~/.openclaw/debate-arena/archives/`

User-supplied debate prompts and debate records can be stored locally and reused as default configuration when explicitly saved.

User impactSaved prompts, role settings, and debate archives may persist across later debates on the same machine.

RecommendationDo not put secrets in debate prompts or speeches, and delete or reset the local config/archive files if you no longer want them reused.

Insecure Inter-Agent Communication

SeverityLowConfidenceHighStatusNote

README.md

The host injects the current group context on `init`, spawns pros/cons/judge for each turn, and archives content + votes locally.

The intended design passes group context and debate content among a host and configured role agents, which is expected for the skill but still involves inter-agent data flow.

User impactThe topic, debate text, votes, and group destination may be shared with the configured debate agents.

RecommendationUse trusted role agents and avoid running debates with sensitive topics in groups or contexts where the participants should not see the content.