Back to skill

Security audit

KimiClaw Bridge

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward setup guide for routing OpenClaw and Claude Code traffic to Kimi, with the main caution that prompts and code will be sent to an external provider.

Before installing or using this skill, confirm that your organization permits sending prompts, repository context, and coding-agent tasks to Kimi. Use real API keys through approved secret management, avoid sending secrets or regulated data, and be careful before setting Kimi as a global default for all spawned agents.

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
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (11)

External Model or Provider Selection

High
Category
Excessive Agency
Confidence
90% confidence
Finding

The skill explicitly redirects Claude Code prompts to a non-default third-party provider, which can materially change where user inputs, code, and agent context are processed. Without a clear warning and consent-oriented language, users may assume they are using the usual backend and unknowingly disclose sensitive data to an external model provider.

Content

Scanner excerpt · SKILL.md (reported line 69)May include surrounding context.

export ANTHROPIC_API_KEY="sk-kimi-..."

claude # Interactive / 交互模式 claude --print "Your prompt" # One-shot / 单次执行

text

Claude Code auto-appends `/v1/messages`. No other changes.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The description declares triggers such as "free coding model" and "kimi code" without clear scope boundaries or negative examples. These phrases are broad enough to match ordinary user discussion rather than an explicit request to invoke this specific skill.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The skill instructs users to route prompts and API credentials to a third-party endpoint but does not clearly warn that prompt contents, code, and possibly sensitive context will leave the local environment. In a coding-agent context, this can lead to inadvertent disclosure of proprietary code, secrets, or regulated data to an external provider.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 37)May include surrounding context.

md
{
  "id": "kimi",
  "type": "anthropic",          // Kimi speaks Anthropic protocol / Kimi 用 Anthropic 协议
  "baseUrl": "https://api.kimi.com/coding",
  "apiKey": "sk-kimi-..."
}

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 65)May include surrounding context.

md
{
  "id": "kimi",
  "type": "anthropic",          // Kimi speaks Anthropic protocol / Kimi 用 Anthropic 协议
  "baseUrl": "https://api.kimi.com/coding",
  "apiKey": "sk-kimi-..."
}

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 105)May include surrounding context.

md
{
  "id": "kimi",
  "type": "anthropic",          // Kimi speaks Anthropic protocol / Kimi 用 Anthropic 协议
  "baseUrl": "https://api.kimi.com/coding",
  "apiKey": "sk-kimi-..."
}

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 106)May include surrounding context.

md
{
  "id": "kimi",
  "type": "anthropic",          // Kimi speaks Anthropic protocol / Kimi 用 Anthropic 协议
  "baseUrl": "https://api.kimi.com/coding",
  "apiKey": "sk-kimi-..."
}

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 118)May include surrounding context.

md
{
  "id": "kimi",
  "type": "anthropic",          // Kimi speaks Anthropic protocol / Kimi 用 Anthropic 协议
  "baseUrl": "https://api.kimi.com/coding",
  "apiKey": "sk-kimi-..."
}

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 133)May include surrounding context.

md
{
  "id": "kimi",
  "type": "anthropic",          // Kimi speaks Anthropic protocol / Kimi 用 Anthropic 协议
  "baseUrl": "https://api.kimi.com/coding",
  "apiKey": "sk-kimi-..."
}

External Transmission

Medium
Category
Data Exfiltration
Confidence
83% confidence
Finding

The spawn example propagates an external API key and routes agent task content to a third-party backend without warning about the sensitivity of spawned task context. In agent workflows, task prompts may include repository code, credentials, or internal data, so embedding this pattern without safeguards increases the chance of accidental data exposure.

Content

Scanner excerpt · SKILL.md (reported line 89)May include surrounding context.

md
runtime="acp",
    task="Refactor auth module to use JWT",
    env={
        "ANTHROPIC_BASE_URL": "https://api.kimi.com/coding",
        "ANTHROPIC_API_KEY": "sk-kimi-..."
    }
)

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 118)May include surrounding context.

Quick Test / 快速验证

bash
curl -s https://api.kimi.com/coding/v1/messages \
  -H "x-api-key: sk-kimi-..." \
  -H "anthropic-version: 2023-06-01" \
  -H "content-type: application/json" \