Security audit

Handwriting Analysis

Security checks for vulnerabilities and agentic risk

Overview

This skill has no executable malware indicators, but it directs agents to make sensitive personality, mental-state, and criminal-risk judgments from handwriting in forensic and personnel contexts.

Install only if you understand this as speculative graphology guidance, not a reliable forensic, hiring, mental-health, or law-enforcement assessment tool. Do not use it to judge a person’s dangerousness, honesty, mental state, employability, or guilt, especially from third-party handwriting without informed consent.

SkillSpector

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
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 (2)

Missing User Warnings

Medium

Confidence: 94% confidence
Finding: The skill invites users to upload handwriting images for analysis without a clear upfront warning that such images may contain sensitive personal data, signatures, identifiers, or contextual clues that could be used for evaluative or investigative judgments. In a forensic/personality-analysis context, this omission increases privacy and misuse risk because users may not understand the sensitivity of what they are submitting or how consequential the inferences may be.

Natural-Language Policy Violations

High

Confidence: 98% confidence
Finding: The skill explicitly instructs the agent to infer personality traits, psychological state, and behavioral tendencies from handwriting as though these are reliable determinations. That is dangerous because it encourages unsupported psychological profiling and potentially forensic conclusions from weak or pseudoscientific signals, which can lead to discriminatory, stigmatizing, or high-stakes errors, especially in criminal-investigative or personnel-evaluation settings.

Static analysis

No suspicious patterns detected.