ClawHub
Back to skill

Security audit

系统控制器

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed system-administration helper, but it gives an agent broad command-execution authority over processes, services, files, environment settings, and scheduled tasks with activation and confirmation scoping that users should review carefully.

Install only if you want an agent to perform real system-administration actions. Review or restrict activation keywords and policy settings before use, require explicit approval for persistent environment changes, cron edits, service enable/disable or restart, permission changes, deletes, and force kills, and verify that audit logs and backups are acceptable for your environment.

SkillSpector

Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

High
Confidence
96% confidence
Finding
The trigger keywords are extremely broad (e.g. “文件/file”, “系统/system”, “control”, “manage”), making the skill likely to activate in many benign contexts and gain access to powerful `exec`-backed system operations without sufficiently specific user intent. In an agent environment, overbroad activation materially increases the chance of unintended process control, file modification, service restarts, or persistence changes.

Missing User Warnings

Medium
Confidence
88% confidence
Finding
The skill supports persistent and system-level changes such as `--persist` environment writes, cron/task creation, service control, and config edits, but the user-facing guidance in this section does not consistently foreground permanence, privilege requirements, rollback limits, or system-wide side effects. This can cause operators or upstream agents to treat sensitive actions as routine configuration, increasing the risk of stealthy persistence or accidental outage.

Static analysis

No suspicious patterns detected.