ClawHub
Back to skill

Security audit

Auto

Security checks for vulnerabilities and agentic risk

Overview

This skill provides straightforward automation guidance for scripts and scheduled jobs, with no bundled code or hidden execution behavior.

Before installing, treat this as a general automation helper: review any generated script before scheduling it, avoid embedding secrets directly in commands, and use least-privilege accounts for jobs that run repeatedly.

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
  • Rogue AgentSelf-Modification, Session Persistence
  • 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
Findings (3)

Vague Triggers

Medium
Confidence
92% confidence
Finding
The manifest description says to use the skill whenever the user wants to script an action, schedule something, automate builds or deploys, or reduce manual workflow steps. This is very broad and could match many ordinary requests, but it does not define clear trigger boundaries or negative examples to distinguish when this skill should not activate.

Vague Triggers

Medium
Confidence
95% confidence
Finding
The phrase “不想每次手动做，想一键/定时跑” describes a very common desire rather than a specific invocation condition. Without tighter scoping, it risks activating the skill for many unrelated conversations about convenience or efficiency.

Session Persistence

Medium
Category
Rogue Agent
Content
### Linux / macOS

- **cron**：`crontab -e`，一行一条。格式：分 时 日 月 周 命令。
  - 每天 9 点：`0 9 * * * /path/to/script.sh`
  - 每 5 分钟：`*/5 * * * * /path/to/script.sh`
- 确保脚本有执行权限（`chmod +x`），必要时在 crontab 里设 `PATH` 或使用绝对路径。
Confidence
85% confidence
Finding
The skill explicitly guides users to establish persistent scheduled execution via cron, which creates durable automation that can continue running without further review. In an automation-focused skill this is expected, but persistence mechanisms can still amplify mistakes, unsafe commands, or abuse if users schedule powerful scripts without guardrails.

Static analysis

No suspicious patterns detected.