Back to skill

Security audit

Handwriting Analysis

Security checks for vulnerabilities and agentic risk

Overview

This skill does not show code-execution or persistence behavior, but it directs the agent to make unsupported personality, mental-state, and criminal-risk judgments from handwriting in investigative and personnel contexts.

Install only if you want a Chinese-language graphology reference for non-consequential, educational exploration. Do not use this skill to judge a person's honesty, mental health, criminal propensity, hiring suitability, or legal responsibility; forensic handwriting questions should be handled by qualified document examiners and supported by independent evidence.

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
Vulnerability Patterns
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (4)

Missing User Warnings

High
Category
Not specified by scanner
Confidence
96% confidence
Finding

This section explicitly maps handwriting features to violent, fraudulent, and premeditated criminal tendencies, which encourages unsupported personality and criminal-risk inference from handwriting. In a forensic/investigative skill, that can mislead users into profiling suspects, reinforcing bias, and causing real-world harm despite the later disclaimer that such analysis is only auxiliary.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill explicitly instructs the model to infer personality traits, psychological state, and behavioral tendencies from handwriting, including for criminal investigation and personnel evaluation. Even though it includes a general limitations disclaimer, it does not clearly warn against making sensitive personal judgments or explain that such inferences are unreliable and can lead to unfair profiling, stigmatization, or harmful downstream decisions.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The document is entirely written in Chinese and does not indicate that language selection is optional or that the skill supports other locales. Under the stated policy, forcing a specific language without user opt-in is a natural-language policy violation unless the locale restriction is explicitly documented and justified.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
86% confidence
Finding

This markdown file is entirely presented in Chinese, beginning with a Chinese title, and nowhere indicates that the language choice is optional or region-specific. Under the policy criteria, forcing a specific language without user opt-in can be a natural-language policy violation.

Content

No source excerpt is available for this finding.