Back to skill

Security audit

whatsapp-monitor

Security checks for vulnerabilities and agentic risk

Overview

This skill is Review-worthy because it monitors private WhatsApp chats and exports matches to Feishu while leaving privacy, credential, and network exposure safeguards under-scoped.

Install only if you are authorized to monitor the specific WhatsApp chats and export their contents to Feishu. Keep the OpenClaw gateway bound to localhost or protect it with authenticated TLS, avoid opening the port broadly, store Feishu secrets outside plaintext config where possible, do not use the config-printing command with real secrets, pin dependencies, and review setup/reset commands before running them on an existing deployment.

Vulnerability Patterns
  • Insecure DependenciesIntroduces malicious components through unsafe dependency sources
  • 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
Findings (6)

T09 · Insecure Skill Coding Practices

Error
Location
scripts/config_manager.py:133
Finding

Plaintext Storage of Feishu Credentials and Private WhatsApp Messages

Content
View full analysis
Remediation
View remediation

T09 · Insecure Skill Coding Practices

Error
Location
run_skill.sh:77
Finding

Feishu Credentials Exposed Through the Configuration Command

Content
View full analysis
Remediation
View remediation

T09 · Insecure Skill Coding Practices

Error
Location
scripts/whatsapp_client.py:19
Finding

Unauthenticated Plaintext Access to the OpenClaw WhatsApp Gateway

Content
View full analysis
Remediation
View remediation

T09 · Insecure Skill Coding Practices

Warning
Location
scripts/message_processor.py:100
Finding

Regular Expression Denial of Service in Message Filtering

Content
View full analysis
Remediation
View remediation

T08 · Insecure Dependencies

Warning
Location
requirements.txt:2
Finding

Automatic Installation of Unpinned Third-Party Dependencies

Content
View full analysis
=3.8.0 pydantic>=2.0.0 python-dateutil>=2.8.0 requests>=2.28.0 pyyaml>=6.0 ``` ```bash for pkg in pyyaml aiohttp pydantic requests python-dateutil; do echo "Installing ${pkg}..." "${PYTHON}" -m pip install "${pkg}" --quiet done ``` ```bash if ! "${PYTHON}" -c "import aiohttp, pydantic, yaml, requests" &>/dev/null; then echo "[WARNING] Some dependencies missing. Installing..." if ! "${PYTHON}" -m pip install -r requirements.txt --quiet; then echo "[ERROR] Failed to install dependencies" exit 1 fi fi ``` ### Technical Analysis The dependency file provides only lower bounds and no upper bounds, exact versions, hashes, or lock file. The dedicated installer is weaker still: it installs package names directly without applying even the stated minimum constraints. Runtime launchers automatically invoke `pip` when imports are missing. Consequently, installations are not reproducible and may retrieve future package releases that were not present during this audit. Python package installation may execute package build logic, and imported packages execute module initialization code under the privileges of the user running the Skill. The reviewed package names are legitimate and no typosquatted package was identified. The vulnerability is the unsafe and implicit dependency acquisition process rather than evidence that the current packages are malicious. ### Attack Path 1. A dependency publisher account, release process, package index route, or future package release is compromised. 2. A user runs the installer or starts the Skill on a system where one of the imports is missing. 3. `pip` resolves an unpinned current release from the package index. 4. Malicious installation or imp ...[truncated 552 chars]
Remediation
View remediation

T09 · Insecure Skill Coding Practices

Warning
Location
scripts/setup.py:125
Finding

Setup Script Overwrites Existing Configuration and Project Files Without Confirmation

Content
View full analysis
Remediation
View remediation
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Tool MisuseTool Parameter Abuse, Chaining Abuse, Unsafe Defaults
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Behavioral ASTexec() Call, eval() Call, Dynamic Import
Findings (61)

Missing User Warnings

High
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill explicitly enables continuous monitoring of WhatsApp chats and export of matching message content, sender data, and timestamps to Feishu, but it does not prominently warn users about privacy, consent, cross-system data sharing, or legal/compliance implications. In this context, the absence of clear disclosure and guardrails materially increases the risk of unauthorized surveillance, collection of third-party communications, and improper exfiltration of sensitive data to another platform.

Content

No source excerpt is available for this finding.

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 53)May include surrounding context.

md
python scripts/setup.py

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 159)May include surrounding context.

md
python scripts/setup.py

Tool Parameter Abuse

High
Category
Tool Misuse
Confidence
85% confidence
Finding

Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).

Content

Scanner excerpt · USAGE.md (reported line 288)May include surrounding context.

bash
# 删除所有数据和日志
rm -f data/matched_messages.json
rm -f logs/whatsapp-monitor.log

# 重置配置文件

Tool Parameter Abuse

High
Category
Tool Misuse
Confidence
85% confidence
Finding

Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).

Content

Scanner excerpt · USAGE.md (reported line 289)May include surrounding context.

bash
# 删除所有数据和日志
rm -f data/matched_messages.json
rm -f logs/whatsapp-monitor.log

# 重置配置文件
rm -f config/whatsapp-targets.json

Tool Parameter Abuse

High
Category
Tool Misuse
Confidence
85% confidence
Finding

Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).

Content

Scanner excerpt · USAGE.md (reported line 292)May include surrounding context.

rm -f logs/whatsapp-monitor.log

重置配置文件

rm -f config/whatsapp-targets.json rm -f config/feishu-settings.json python scripts/setup.py

text

Tool Parameter Abuse

High
Category
Tool Misuse
Confidence
85% confidence
Finding

Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).

Content

Scanner excerpt · USAGE.md (reported line 293)May include surrounding context.

重置配置文件

rm -f config/whatsapp-targets.json rm -f config/feishu-settings.json python scripts/setup.py

text

Credential Access

High
Category
Privilege Escalation
Confidence
60% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · load_skill.py (reported line 229)May include surrounding context.

python
env/
venv/
.venv/
.env
*.log
"""
            with open(gitignore_path, 'w', encoding='utf-8') as f:

Missing User Warnings

High
Category
Not specified by scanner
Confidence
98% confidence
Finding

The skill description explains how to trigger WhatsApp monitoring and export behavior but does not clearly warn users that it processes potentially sensitive private communications. In a messaging-monitoring context, missing privacy and consent warnings can lead to deployment without informed consent, creating serious confidentiality, compliance, and insider-misuse risks.

Content

No source excerpt is available for this finding.

Credential Access

High
Category
Privilege Escalation
Confidence
70% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · references/openclaw_whatsapp_integration.md (reported line 54)May include surrounding context.

  1. 获取 API 凭证

    • 访问 Facebook Developer Portal
    • 创建 WhatsApp Business 应用
    • 获取 Phone Number ID 和 Access Token
  2. 配置 OpenClaw

    yaml

Missing User Warnings

High
Category
Not specified by scanner
Confidence
95% confidence
Finding

The generated README instructs users to monitor WhatsApp messages and export their contents, senders, attachments, and chat links to Feishu, but it does not warn about consent, privacy, retention, or legal/compliance implications. In this skill context, that omission is materially risky because the tool is explicitly designed for surveillance-like collection and third-party transfer of potentially sensitive communications.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The file begins in English but switches into Chinese for key setup and workflow instructions, which can impose a specific language on users without opt-in. There is no statement that the skill is intended only for Chinese-speaking users or that alternative language documentation is available.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The guide describes continuous monitoring of WhatsApp messages, keyword filtering, storage, and export to Feishu, but it does not warn users about privacy, consent, data retention, or cross-system sharing of message content. This omission can lead to unauthorized surveillance or mishandling of personal/business communications, especially because the skill processes sensitive chat data by design.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The reset section instructs users to delete message data, logs, and configuration files without clearly warning that the action is irreversible and may erase audit trails and credentials/configuration state. In operational environments, this can cause accidental data loss and hinder forensic review or recovery after incidents.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
82% confidence
Finding

The natural-language content in target names, identifiers, and keyword lists is entirely Chinese, which suggests the skill is configured for a specific language/locale by default. There is no indication in this file that users can choose another language or that the locale restriction is explicitly documented as intentional and justified.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
87% confidence
Finding

The keyword list contains broad, common terms such as '问题', '帮忙', and '会议' that are likely to appear in many normal conversations. In a monitoring configuration, this can cause over-collection, false alerts, or unintended actions against chats or contacts that were not meant to be monitored, increasing privacy and operational risk.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

This Python file contains user-facing natural-language strings and documentation entirely in Chinese, including the module description and later console output, with no indication that language selection is optional. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation unless the locale restriction is clearly justified.

Content

No source excerpt is available for this finding.

Dynamic import via __import__()

Medium
Category
Dangerous Code Execution
Confidence
75% confidence
Finding

Dynamic import() can load arbitrary modules at runtime, bypassing static analysis and potentially importing malicious code.

Content

Scanner excerpt · load_skill.py (reported line 61)May include surrounding context.

python
missing_packages = []
    for package in required_packages:
        try:
            __import__(package)
        except ImportError:
            missing_packages.append(package)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The documented trigger conditions are broad enough that a general conversation mentioning WhatsApp monitoring concepts could activate the skill unintentionally. Because this skill monitors and exports private messages, accidental activation increases the risk of unauthorized surveillance, collection, or forwarding of sensitive communications.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The document states that the skill monitors WhatsApp messages and later documents endpoints for reading chats/messages and sending messages, which can affect user privacy and communications. Although there is a later generic security section, it does not clearly warn users up front that the integration can access message contents and send messages on their behalf.

Content

No source excerpt is available for this finding.

Internal Network Request

Medium
Category
Server-Side Request Forgery
Confidence
70% confidence
Finding

Code issues a request to a loopback, link-local, or private-range host. This can reach internal services not meant to be exposed and is a common SSRF pivot.

Content

Scanner excerpt · references/port_configuration.md (reported line 142)May include surrounding context.

curl http://localhost:18789/health

或使用 Python

python -c "import requests; r = requests.get('http://localhost:18789/health'); print(r.status_code)"

text

### 7. 防火墙配置

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
86% confidence
Finding

The document gives explicit instructions to open a firewall port and enable network access, but it does not warn that doing so can expose the OpenClaw Gateway to other hosts and increase attack surface. In a skill context, operational guidance that changes host firewall posture without security caveats can lead users to unintentionally expose sensitive APIs or monitoring infrastructure.

Content

No source excerpt is available for this finding.

Sudo/Root Execution

Medium
Category
Privilege Escalation
Confidence
70% confidence
Finding

Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.

Content

Scanner excerpt · references/port_configuration.md (reported line 152)May include surrounding context.

Linux 防火墙:

bash
# Ubuntu/Debian
sudo ufw allow 18789/tcp

# CentOS/RHEL
sudo firewall-cmd --permanent --add-port=18789/tcp

Sudo/Root Execution

Medium
Category
Privilege Escalation
Confidence
70% confidence
Finding

Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.

Content

Scanner excerpt · references/port_configuration.md (reported line 155)May include surrounding context.

Linux 防火墙:

bash
# Ubuntu/Debian
sudo ufw allow 18789/tcp

# CentOS/RHEL
sudo firewall-cmd --permanent --add-port=18789/tcp

Sudo/Root Execution

Medium
Category
Privilege Escalation
Confidence
70% confidence
Finding

Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.

Content

Scanner excerpt · references/port_configuration.md (reported line 156)May include surrounding context.

Linux 防火墙:

bash
# Ubuntu/Debian
sudo ufw allow 18789/tcp

# CentOS/RHEL
sudo firewall-cmd --permanent --add-port=18789/tcp