ClawHub
Back to skill

Security audit

第一性原理思维框架，基于 SACL 方法论。帮助你在资源有限时，通过剥离层-基元化-约束映射-杠杆重构，找到破局点和不对称优势。

Security checks for vulnerabilities and agentic risk

Overview

This is a markdown-only reasoning framework skill with broad but disclosed activation language and no commands, persistence, credential access, or hidden data flows.

Install this if you want a structured first-principles thinking aid. Be aware it may activate for broad problem-solving requests, and some examples discuss tactics like scraping public questions, so users should keep legal, platform, and preference constraints in mind when applying its advice.

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
  • 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (4)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill description defines very broad activation conditions such as complex problems, bottlenecks, limited resources, and common phrases like 'first principles' or 'break down problems'. This can cause the skill to activate for a wide range of ordinary user requests, potentially overriding more specific domain skills or steering conversations into an unintended framework, which is a prompt-scope security and reliability issue even without malicious content.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The usage examples include highly generic trigger phrases like 'How do I break down this complex problem?' and 'I'm stuck because I can't solve a sub-problem,' which overlap with many normal assistant interactions. In context, this increases the chance of over-triggering the skill and inappropriately biasing responses toward this framework, reducing routing precision and creating prompt-scope interference.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
91% confidence
Finding

This markdown file contains user-facing instructions exclusively in Chinese, including the title, descriptions, and usage guidance. Under the policy, forcing a specific language without user opt-in can be a natural-language policy violation when no alternative language option or justification is provided.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

The manifest description embeds Chinese trigger phrases alongside English guidance, which creates an implicit locale assumption without stating whether multilingual behavior is optional or user-driven. Under the policy, language behavior should be explicitly offered as a choice or clearly justified.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.