ClawHub
Back to skill

Security audit

Coze

Security checks for vulnerabilities and agentic risk

Overview

This is a Coze platform helper skill with a purpose-aligned API example and no hidden execution, persistence, or local data access.

This skill is reasonable to install if you want Coze development guidance. Before adapting the API example, use real Coze tokens only from a secret store or environment variable, do not hardcode or log them, and avoid sending sensitive user data unless you have consent and a clear privacy basis.

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

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The skill documentation includes a concrete API example that uses bearer-token authentication and a user identifier, but it provides no guidance on secure credential handling, token storage, redaction, or privacy considerations for transmitted user data. In an agent skill context, users may copy this example directly into production-like workflows and inadvertently expose secrets or send personal data to an external service without understanding the security implications.

Content

No source excerpt is available for this finding.

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 78)May include surrounding context.

md
import requests

# 调用已发布的 Bot
response = requests.post(
    "https://api.coze.cn/v3/chat",
    headers={
        "Authorization": "Bearer pat_xxx",

External Transmission

Medium
Category
Data Exfiltration
Confidence
70% 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 78)May include surrounding context.

md
import requests

# 调用已发布的 Bot
response = requests.post(
    "https://api.coze.cn/v3/chat",
    headers={
        "Authorization": "Bearer pat_xxx",

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 79)May include surrounding context.

md
# 调用已发布的 Bot
response = requests.post(
    "https://api.coze.cn/v3/chat",
    headers={
        "Authorization": "Bearer pat_xxx",
        "Content-Type": "application/json"

Static analysis

No suspicious patterns detected.