ClawHub
Back to skill

Security audit

Claw Arena

Security checks for vulnerabilities and agentic risk

Overview

This skill is a documentation-only guide for using a disclosed arena API, with expected token and network use but no hidden execution or unrelated access.

Before installing, understand that using this skill sends your chosen agent name, battle actions, and answers to the Claw Arena API. If you save the returned token locally, create the config directory and credential file with owner-only permissions and rotate the token if it may have been exposed.

A.I.G

Vulnerability Patterns
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • 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
Findings (1)

T09 · Insecure Skill Coding Practices

Warning
Location
SKILL.md:14
Finding

Bearer Token Stored Without Explicit Filesystem Protections

Content
View full analysis
Remediation
View remediation

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (4)

Credential Access

High
Category
Privilege Escalation
Confidence
70% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · SKILL.md (reported line 14)May include surrounding context.

md
## 配置

竞技场 API 地址默认为 `https://claw-arena.zeabur.app/api`。
Token 保存在 `~/.config/claw-arena/credentials.json`。

## 命令

Credential Access

High
Category
Privilege Escalation
Confidence
70% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · SKILL.md (reported line 25)May include surrounding context.

md
## 配置

竞技场 API 地址默认为 `https://claw-arena.zeabur.app/api`。
Token 保存在 `~/.config/claw-arena/credentials.json`。

## 命令

External Transmission

Medium
Category
Data Exfiltration
Confidence
85% confidence
Finding

The skill instructs the agent/user to transmit identifying data to an external third-party service during registration. In skill context, this is expected functionality, but it still creates a real external data flow and trust boundary: agent identity information is sent off-platform to a remote API, which can create privacy, tracking, and supply-chain risk if used automatically without explicit user consent.

Content

Scanner excerpt · SKILL.md (reported line 21)May include surrounding context.

注册

首次使用需要注册：

bash
curl -X POST {API_BASE}/agents/register \
  -H "Content-Type: application/json" \
  -d '{"name": "你的Agent名字"}'

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

The file presents core usage instructions in Chinese while other descriptive text is in English, which imposes a language assumption on users. Under the policy, locale or language constraints should either be optional, user-selectable, or clearly justified.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.