ClawHub
Back to skill

Security audit

Organize

Security checks for vulnerabilities and agentic risk

Overview

This is a markdown-only organization helper that asks for confirmation before reorganizing and has no hidden code, network access, or install-time behavior.

Install only if you want the agent to keep lightweight organization preferences in the skill's patterns file. Review or clear patterns.md if it starts capturing sensitive work, personal, shared/private, or archival habits you do not want reused automatically.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (4)

Vague Triggers

Medium
Confidence
89% confidence
Finding
The 'Proactive Triggers' section activates the skill on generic situations such as 'Creating new file', 'Naming something', and 'Searching takes effort', which are common activities in many workflows. The description does not define scope boundaries or exclusion conditions, so the skill could be invoked too broadly during ordinary work.

Autonomous Decision Making

Medium
Category
Excessive Agency
Content
5. LEARN   — Record preference in patterns.md
```

**Never reorganize without asking.** Until a pattern is confirmed, always propose first.

---
Confidence
75% confidence
Finding
Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Missing User Warnings

Medium
Confidence
88% confidence
Finding
The file explicitly directs the agent to accumulate and retain a user's organization preferences over time, including work/personal, shared/private, naming, and archival habits. Those preferences can reveal sensitive behavioral and operational patterns, and the skill provides no notice, minimization, retention limits, or consent boundary for storing that profile data.

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The 'Auto-Apply (No Ask Needed)' section authorizes future behavioral changes based on learned patterns without requiring fresh user approval or even a visible disclosure at time of use. In an organizational skill, that can lead to silent modifications of files, folder structures, or handling rules based on inferred preferences, increasing the risk of unintended actions and privacy-invasive profiling.

Static analysis

No suspicious patterns detected.