ClawHub
Back to skill

Security audit

EC Price Monitor Pro

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed price-monitoring skill with expected web checks, local price history, and optional notification delivery, but users should review the recurring scan and webhook settings before enabling it.

Install only if you want an hourly price monitor. Review references/config.yaml before use, remove sample products, leave Feishu/Telegram fields blank unless you want reports sent to those services, and treat any configured webhook or bot token as sensitive.

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
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (8)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
91% confidence
Finding

The skill advertises network-dependent behavior such as multi-platform price checks, license purchase/activation flow, and outbound push notifications, but it does not declare any explicit tool scope or permissions. This creates a transparency and policy gap: users and the platform cannot clearly see or constrain external network access, increasing the risk of unintended data transmission or overbroad runtime capabilities.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The skill describes hourly automatic scanning and push delivery to Feishu/Telegram without a clear warning that it will perform recurring background network requests and send outbound notifications. In practice, this can surprise users, leak monitored product interests or identifiers to third parties, and generate ongoing external activity after initial setup.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill transmits generated reports and price alerts to external Feishu and Telegram endpoints based on configuration, but the file itself provides no explicit warning, consent flow, or data-minimization controls. Even if intended as a feature, report contents can include user-supplied keywords and monitoring results, which creates a privacy and data-exfiltration risk if users do not realize external delivery is enabled.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
92% confidence
Finding

This code performs outbound HTTP transmission of message content to a configured webhook URL without any validation of destination trustworthiness or clear in-file disclosure. Because the webhook is configurable, sensitive monitoring data could be sent to an attacker-controlled endpoint if the configuration is modified or misunderstood.

Content

Scanner excerpt · scripts/price_monitor_pro.py (reported line 143)May include surrounding context.

python
if webhook:
        try:
            data = json.dumps({"msg_type": "text", "content": {"text": message[:3000]}}).encode()
            urllib.request.urlopen(urllib.request.Request(webhook, data=data,
                headers={"Content-Type": "application/json"}), timeout=5)
        except: pass
    tg_token = notify.get("telegram_token", "")

External Transmission

Medium
Category
Data Exfiltration
Confidence
90% confidence
Finding

The skill sends report text to Telegram using a bot token and chat ID, which is an external transmission channel carrying user-generated monitoring content. While this appears intentional, it still creates a confidentiality risk if users are unaware, if tokens/chat IDs are misconfigured, or if sensitive product-monitoring data should not leave the local environment.

Content

Scanner excerpt · scripts/price_monitor_pro.py (reported line 152)May include surrounding context.

python
try:
            text = urllib.parse.quote(message[:4000])
            urllib.request.urlopen(
                f"https://api.telegram.org/bot{tg_token}/sendMessage?chat_id={tg_chat}&text={text}", timeout=5)
        except: pass

# ── 主动执行 ──

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
93% confidence
Finding

The natural-language content of the skill forces a single language/locale for description, commands, and usage guidance. Under the policy, this is a language/locale constraint that should either offer user choice or clearly document a justified regional limitation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
76% confidence
Finding

The comment "EC Price Monitor Pro - 配置" is natural-language content indicating the skill/configuration is presented in Chinese, but this file does not document any user opt-in or locale choice. Under the policy rule for language/locale constraints, forcing a specific language without explicit choice can be a policy concern.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
89% confidence
Finding

The module description and all user-facing console messages are written in Chinese, which imposes a specific language on users without any opt-in or documented locale constraint. Under the policy, hardcoded language restrictions should be avoided unless the skill explicitly offers a choice or clearly justifies a region-specific limitation.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.