ClawHub
Back to skill

Security audit

自动化工作流设计

Security checks for vulnerabilities and agentic risk

Overview

This is a plain automation-advice skill with some broad and sensitive workflow examples, but no hidden code, installation behavior, or deceptive instructions.

Before installing, be aware that this skill may be invoked for broad productivity wording and that its examples include automating customer, payment, CRM, and outbound email actions. Use test data first, grant only the minimum app permissions needed, review mappings carefully, and add human approval for financial updates or customer-facing messages.

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
  • Rogue AgentSelf-Modification, Session Persistence
  • 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)

Vague Triggers

Medium
Confidence
97% confidence
Finding
The trigger phrases are broad enough to activate on many normal user requests about saving time or reducing manual work, which can cause unintended routing to this skill. Over-broad invocation increases the chance that the agent applies automation guidance in contexts where the user did not explicitly request workflow design, leading to irrelevant or risky operational suggestions.

Missing User Warnings

Medium
Confidence
90% confidence
Finding
The skill encourages moving customer and business data across CRMs, spreadsheets, email tools, accounting systems, and messaging platforms without explicit safeguards around consent, least-privilege access, data minimization, or validation. This can lead users to build automations that leak personal or financial data, corrupt records, or trigger unintended external actions at scale.

Session Persistence

Medium
Category
Rogue Agent
Content
2. Flag customers with <50% of average usage
  3. Add flagged customers to "At Risk" segment in CRM
  4. Send re-engagement email campaign to at-risk customers
  5. Create task for me to personally reach out to top 10 at-risk customers
```

### Invoice and payment tracking
Confidence
80% 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.

Static analysis

No suspicious patterns detected.