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
Category
Not specified by scanner
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.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
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.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
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.

Content

No source excerpt is available for this finding.