ClawHub
Back to skill

Security audit

钉钉快速集成配置

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent DingTalk integration guide, but users should handle webhook secrets and business messages carefully.

Before installing, make sure the DingTalk webhook token and signing secret are not committed, logged, screenshotted, or shared. Restrict the config file permissions, rotate the webhook if exposed, and avoid sending customer, employee, approval, or incident details to DingTalk unless that group is approved for that data.

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:38
Finding

Plaintext Storage of DingTalk Bot Credentials

Content
View full analysis
Remediation
View remediation

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (5)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The skill instructs users to place a DingTalk webhook URL and signing secret directly into a local config file and discusses testing with those values, but provides no guidance on secret storage, file permissions, redaction, or rotation. This creates a realistic risk of credential leakage through source control, shell history, screenshots, support logs, or overly permissive config files, which could let an attacker send messages to enterprise DingTalk groups.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The skill promotes automated daily reports, infrastructure alerts, and approval processing without warning that operational, business, or approval data may be transmitted to DingTalk. In an enterprise context, this can cause unintended disclosure of sensitive internal data, especially if alerts or approval payloads include customer, employee, or system details.

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 159)May include surrounding context.

  1. 确认机器人未被删除
  2. 测试 URL 可达性：
    bash
    curl -X POST "YOUR_WEBHOOK_URL" \
  -H "Content-Type: application/json" \
  -d '{"msgtype":"text","text":{"content":"测试"}}'

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
82% confidence
Finding

The description explicitly targets Chinese enterprise users and the entire skill is presented only in Chinese. Per the language/locale policy rule, forcing a specific language without user opt-in or a clearly documented region-specific justification can be a natural-language policy violation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

The skill name, description, and keywords indicate a China/Chinese-specific experience (e.g. "cn", Chinese-language description, and "chinese" keyword), but the manifest does not state that this locale restriction is optional or justified by a region-specific compliance requirement. This can conflict with language/locale policy when users are not given a choice or informed of the constraint.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.