ClawHub
Back to skill

Security audit

监控工具包-免费版

Security checks across malware telemetry and agentic risk

Overview

This monitoring skill is review-worthy because it can run user-defined shell commands and send alert data to webhooks without tight boundaries.

Install only if you are comfortable with the agent running shell commands for monitoring. Keep custom checks limited to commands you understand, use approved webhook destinations, avoid embedding secrets in monitor configs or curl headers, and review any scheduled or repeated execution before enabling it.

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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
Findings (3)

Context-Inappropriate Capability

Medium
Confidence
94% confidence
Finding
The documented `custom` check type explicitly allows user-specified commands, which turns a monitoring skill into a generic command-execution surface. In an agent context with the `exec` tool enabled, this can be abused to run arbitrary shell commands, leading to local command execution, data access, persistence, or lateral movement well beyond the stated monitoring scope.

Vague Triggers

Medium
Confidence
84% confidence
Finding
The trigger condition is broad enough to activate the skill for general system monitoring, log analysis, alerting, or deployment-related requests, increasing the chance of unintended invocation. In an agent environment, overbroad triggering can cause the skill to run commands or send alerts in contexts the user did not specifically intend, which raises the risk of unsafe execution or data disclosure.

Missing User Warnings

Medium
Confidence
89% confidence
Finding
The webhook alerting behavior sends monitoring status, target identifiers, and timestamps to external URLs without an explicit warning about external data transmission or validation of destination trust. This can lead to accidental exfiltration of internal service names, health states, or operational metadata to third-party endpoints controlled by an attacker or misconfigured by the user.

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal

Static analysis

No suspicious patterns detected.