ClawHub
Back to skill

Security audit

Super Automation

Security checks for vulnerabilities and agentic risk

Overview

This skill gives user-directed guidance for creating scripts and scheduled automation, with no bundled executable code or hidden behavior found.

Install this only if you want a broad automation helper. Review any generated cron, Task Scheduler, CI/CD, or script commands before running them, especially commands that run repeatedly, modify files, deploy code, or use credentials.

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
Category
Not specified by scanner
Confidence
93% confidence
Finding

The manifest description says the skill is ideal for automating 'any scriptable procedure or scheduled routine,' which is extremely broad for activation guidance in a manifest file. This lacks clear trigger constraints or exclusions, increasing the chance of unintended invocation for general productivity or scripting requests.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The activation guidance includes generic conditions like 'batch process files, fetch data, send notifications' and the phrase '不想每次手动做，想一键/定时跑,' which can apply to many ordinary requests outside a well-scoped automation skill. The file does not provide negative examples or boundaries to distinguish intended automation cases from general help requests.

Content

No source excerpt is available for this finding.

Session Persistence

Medium
Category
Rogue Agent
Confidence
85% confidence
Finding

Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Content

Scanner excerpt · SKILL.md (reported line 43)May include surrounding context.

md
### 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。