ClawHub
Back to skill

Security audit

Judgment_Enhancement_Engine

Security checks for vulnerabilities and agentic risk

Overview

This skill is a local Python decision-support library with documentation issues but no evidence of hidden access, exfiltration, persistence, or destructive behavior.

Reasonable to install if you want a small local Python decision-making demo/library. Review the Chinese-only reference docs and the inaccurate CognitiveEnhancer/setup.bat references before relying on it in production, and treat it as sample code rather than a polished security-sensitive component.

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
  • Memory PoisoningPersistent Context Injection, Context Window Stuffing, Memory Manipulation
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • 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 (8)

Tp4

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

The declared description describes a substantive decision-support engine with advanced evaluation capabilities. The supplied code chunk does not implement any of that functionality. It only logs messages indicating that tests are skipped and that the real engine is in Python. While this may be a supporting script within a larger project, evaluated on its own it materially differs from the declared purpose and lacks the described capabilities.

Content

No source excerpt is available for this finding.

Memory Manipulation

High
Category
Memory Poisoning
Confidence
80% confidence
Finding

Skill manipulates agent memory, state, or stored context. Memory corruption can alter personality, override safety rules, or cause unpredictable behavior.

Content

Scanner excerpt · SKILL.md (reported line 63)May include surrounding context.

5. Record actual outcome (for historical correction)

engine.record_outcome(state, action, actual_utility)

6. Optional: clear history

engine.clear_history()

text

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

This markdown file is written entirely as a Chinese-language specification, including all parameter descriptions, method behavior, and error semantics, with no indication that another language is supported or that Chinese is a required locale. Under the policy rule for natural-language violations, forcing a specific language without user opt-in is a reportable issue unless the locale restriction is explicitly justified.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
83% confidence
Finding

The manifest describes this skill as providing judgment enhancement through lookahead, risk-adjusted utility, and historical reflection for evaluating action consequences under uncertainty. In contrast, the guide presents the skill file as exposing or integrating a broader 'CognitiveEnhancer' that provides memory recall, which is a distinct cognitive capability not described in the manifest.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Low
Category
Not specified by scanner
Confidence
97% confidence
Finding

The header comment says both 'pure Node.js info module' and 'Pure Python engine. This file provides metadata only.' Those statements conflict with each other about the nature of the module, which is an intent/documentation contradiction rather than a mere omission.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
97% confidence
Finding

This markdown file contains user-facing instructional content exclusively in Chinese, and there is no indication that users can choose another language or that the skill is intentionally limited to a Chinese-speaking audience. Under the policy rule for language/locale constraints, forcing a specific language without opt-in is a natural-language policy issue.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
87% confidence
Finding

The file begins with a Chinese-only natural-language title, "判断力增强引擎 — 基础功能测试," with no indication that language selection is optional or that the skill is region-specific. Under the policy rule for natural-language violations, this can be considered a locale/language constraint without user opt-in.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Low
Category
Not specified by scanner
Confidence
97% confidence
Finding

The header identifies the file as a "Node.js client test" but immediately states "Pure Python execution," which contradicts the actual code that uses Node.js syntax and the Node path module. This is an active documentation contradiction rather than a mere omission, because a reader could misunderstand how this file is meant to run.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.