ClawHub
Back to skill

Security audit

Coze 工作流执行 / Coze Workflow

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Coze workflow caller that sends user-provided workflow parameters to Coze using a user-supplied API key.

Install only if you intend to send workflow inputs and outputs through Coze. Use a least-privilege Coze API token, keep the config file private, avoid placing secrets or sensitive personal data in workflow parameters unless appropriate for your Coze account and workflows, and rotate the token if the file 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:31
Finding

Plaintext Storage of Coze API Bearer Token

Content
View full analysis
Remediation
View remediation

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 (3)

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 83)May include surrounding context.

方法 1：流式执行（推荐）/ Method 1: Stream (Recommended)

bash
curl -X POST "${COZE_BASE_URL}/v1/workflow/stream_run" \
  -H "Authorization: Bearer ${COZE_API_KEY}" \
  -H "Content-Type: application/json" \
  -d '{

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 · config.json (reported line 3)May include surrounding context.

json
{
  "api_key": "你的扣子api key",
  "base_url": "https://api.coze.cn/v1/workflow/stream_run"
}

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

The placeholder string for the API key is written only in Chinese ("你的扣子api key"), which imposes a specific language in user-facing configuration text without offering a language choice or neutral wording. This can violate language/locale policy when the skill is not explicitly documented as Chinese-only or region-specific.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.