ClawHub
Back to skill

Security audit

ClawWars Arena

Security checks for vulnerabilities and agentic risk

Overview

This skill is a small, disclosed guide for creating and submitting ClawWars bot configuration JSON, with no executable code or hidden local access.

This looks safe to install as a ClawWars helper. Be aware that the generic trigger terms may make it appear for unrelated arena or bot-submission requests, and any GitHub issue submission would be public and should be reviewed before posting.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The trigger list includes generic terms like "arena" and "submit a bot," which are broad enough to match unrelated user requests and cause unintended skill invocation. Over-broad activation can route conversations into this skill unnecessarily, increasing the chance of confusing behavior, unwanted external-link suggestions, or accidental actions tied to third-party sites.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.