ClawHub
Back to skill

Security audit

Understand Me

Security checks for vulnerabilities and agentic risk

Overview

This is a thinking-partner skill that may read user-provided materials, but it does not install code, persist changes, access credentials, or perform high-impact actions.

Install this if you want a direct, structured critique workflow for ideas and documents. Be aware that its broad triggers may make it engage during general brainstorming, and it may read files or materials you explicitly provide so it can avoid asking redundant questions.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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
94% confidence
Finding

The manifest description is broad enough to activate on very common requests like understanding, refining, or challenging ideas, which can cause the skill to trigger outside a narrowly intended scope. Overbroad routing increases the chance that this skill intercepts unrelated tasks and applies its forceful workflow or document-search behavior where a more appropriate, safer skill should have been used.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The trigger examples include broad, everyday phrases such as 'challenge my idea' and '帮我把这个方案想清楚', which are common across many benign conversations and therefore make unintended activation likely. In an agent environment, ambiguous triggers can lead to prompt/skill squatting, where this skill captures user intent too aggressively and influences behavior beyond its intended niche.

Content

No source excerpt is available for this finding.

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
80% 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.

Content

Scanner excerpt · SKILL.md (reported line 113)May include surrounding context.

md
2. Cite the source path/section briefly.
3. Only ask the user if the material is missing, contradictory, outdated, or ambiguous.

Do not ask the user to repeat facts that are already in their provided materials.

### Step 5 — Resolve dependencies progressively

Static analysis

No suspicious patterns detected.