Skills/ClawHub/the-arena

the-arena@1.3.0

CAUTION· static only

Publisher claims: "Turn a Discord server into a moderated debate arena with an AI judge. Supports multiple debate formats, configurable personas, scored verdicts, and a persist..." Observed in sandbox: static analysis only — behavior not yet observed.

Registry ClawHubPublisher tdavis009 · publishing for 276 daysInstalls 2,008Last detonated 27 min ago

Coverage

Static only; nothing was run yet.

The label rests on the code, the instruction files and the publisher. The honeypot run replaces this verdict when it completes.

Is [email protected] safe to install?

KillerSkills analysed it statically (a sandbox run is pending) on 2026-11-21 and scored it 70/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Authorization escalation language; Prompt injection; Authorization escalation language. Summary: static analysis only — behavior not yet observed.

Behavior trace

Queued for honeypot run · static analysis only
t+CategoryObserved action

This version has not been detonated yet. The score above counts behavior as unknown (50/100), so it cannot read Verified until the honeypot run completes and replaces this verdict.

Static findings

LOW
Prompt injectionreferences/setup-guide.md:31 · Prompt injection — known jailbreak technique reference · informational: not an instruction file1. In Discord, go to Settings → Advanced → Enable **Developer Mode**Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
HIGH
Authorization escalation languageSKILL.md:32 · Authorization escalation language| **Gateway admin access** | You manually review and apply config changes via `config.patch` |Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
Authorization escalation languagereferences/setup-guide.md:12 · Authorization escalation language · informational: not an instruction file- Admin access to the target Discord serverFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
CRITICAL
Prompt injectionSKILL.md:64 · Prompt injection — known jailbreak technique reference(right-click the server icon → Copy Server ID with Developer Mode enabled).Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
HIGH
Authorization escalation languageSKILL.md:64 · Authorization escalation language(right-click the server icon → Copy Server ID with Developer Mode enabled).Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
Authorization escalation languagereferences/setup-guide.md:31 · Authorization escalation language · informational: not an instruction file1. In Discord, go to Settings → Advanced → Enable **Developer Mode**Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01

Cost to the agent

Instructions loaded
≈3,097 tok
1 file · 10 in bundle

Tokens estimated at four characters each. Skills load their instruction text when triggered; the figure is what that costs.

Known vulnerabilities

Vulnerability advisories (OSV) cover npm and PyPI packages; this registry has no advisory database.

What would make this Verified

10 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim tdavis009: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
Publish a new version to ClawHub, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim tdavis009Propose a patch to the maintainer