Back to skill

Security audit

KimiClaw

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-only skill for configuring Kimi as an external coding-model backend, with no hidden code or automatic execution, but users should understand it can route prompts and code to Kimi.

Install this only if you want OpenClaw or Claude Code to use Kimi as a third-party backend. Treat any prompts, repository content, and agent context as data that may be sent to Kimi, avoid placing real API keys in shared config files, and be careful before making Kimi the global default for all spawned coding 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 instructs users to run Claude Code prompts against an alternate external provider with no gating or consent checkpoint. In a coding-agent context, this can redirect sensitive prompts, code, and derived outputs to a third party, which raises meaningful confidentiality and compliance risk.

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
90% confidence
Finding

The trigger list includes broad phrases such as 'free coding model' and 'kimi code', which can match general user requests unrelated to explicit consent to use this third-party provider. That increases the chance the skill is invoked unexpectedly and routes prompts or code to an external service without the user clearly intending that provider selection.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The documentation promotes replacing the backend with Kimi but does not clearly warn that prompts, code, and potentially sensitive workspace data will be transmitted to an external third-party API. In an agent/coding context, this omission is material because users may assume operations remain local or with their default 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 89)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
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" \