ClawHub
Back to skill

Security audit

First Principles Thinking

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed, always-on reasoning-style skill with no code execution, data access, external calls, or persistence beyond normal installation.

Install this only if you want the agent's default behavior to be more questioning, concise, and first-principles oriented across sessions; expect it to challenge unclear requests or suggest simpler alternatives more often.

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
  • 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Vague Triggers

High
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill is explicitly configured with alwaysLoad: true and says it is 'always active,' which gives it effectively global influence over agent behavior regardless of user intent. That broad scope can override or distort other task-specific instructions, create prompt-conflict conditions, and cause the agent to ask unnecessary clarifying questions or reshape workflows in contexts where this framework should not apply.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The file is entirely written as an instruction set in Chinese and presents itself as a mandatory framework that "始终生效", but it does not offer any language choice or say the behavior is limited to Chinese-speaking users. This can impose a specific language or locale policy on interactions without user opt-in.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
86% confidence
Finding

The skill documentation is explicitly bilingual in Chinese and English, but it does not state that users may choose their preferred language or that the skill adapts to user locale. Because this file describes a generally applicable thinking framework rather than a region-specific tool, the fixed language presentation can be read as imposing a locale convention without opt-in.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.