ClawHub
Back to skill

Security audit

FOUDF - 五算子通用决策框架

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed decision-analysis framework with no code execution, data access, persistence, or install-time behavior beyond its markdown instructions.

Install this if you want a structured five-part decision framework, especially for Chinese-language or bilingual use. Be aware that its broad trigger may make answers more formal and framework-driven for many complex questions; it does not itself access files, credentials, network services, or modify your environment.

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 (3)

Natural-Language Policy Violations

Medium
Confidence
91% confidence
Finding
The skill is written primarily in Chinese and strongly frames terminology and output structure in that language without stating that the user's preferred language must be honored. In a multilingual agent setting, this can degrade usability, cause instruction-following conflicts, and increase the chance the assistant responds in an unwanted language or mixes languages unexpectedly.

Vague Triggers

Medium
Confidence
95% confidence
Finding
The trigger condition is extremely broad ('any complex decision with multiple variables, long chains, uncertainty, or tradeoffs') and says the skill should auto-activate. That creates scope hijacking risk: the agent may invoke this framework for many unrelated prompts, overriding more appropriate domain-specific behavior and steering responses into a rigid analysis pattern without explicit user consent.

Natural-Language Policy Violations

Low
Confidence
77% confidence
Finding
The manifest description includes a Chinese-language title segment alongside the English name, which can indicate a language-specific presentation choice without any stated user opt-in or locale constraint. For a policy check focused on language/locale handling, this may violate expectations if the skill presents or prefers a specific language without documenting that choice.

Static analysis

No suspicious patterns detected.