Security audit

AI Density

Security checks for vulnerabilities and agentic risk

Overview

The skill appears non-malicious and local-only, but it presents heuristic AI-authorship guesses as objective, precise human-vs-AI contribution levels.

Install only if you are comfortable treating the result as a rough heuristic signal, not proof of AI authorship or exact human contribution. Avoid using it alone for moderation, academic, hiring, compliance, or other consequential decisions.

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

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
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (6)

Intent-Code Divergence

High

Category: Not specified by scanner
Confidence: 98% confidence
Finding: The returned level descriptions assert precise percentages and attribution such as '人工修改占比≥50%' or '无任何人工参与', but the code does not actually measure provenance, edit history, or contribution percentages. This creates a strong risk of false authority and deceptive output that could be used in moderation, compliance, academic, or employment contexts to make harmful decisions based on unsupported claims.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: This Python skill is heavily hard-coded around Chinese-language labels, warnings, descriptions, and detection patterns, and the returned user-facing result strings are only in Chinese. That creates a natural-language locale policy issue because the skill enforces a specific language without any visible opt-in, configuration, or documented regional limitation.
Content: No source excerpt is available for this finding.

Intent-Code Divergence

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The docstring claims the component uses NLP perplexity, but the implementation only derives heuristic proxies from regexes, sentence-length variance, and token diversity. In a tool marketed as an objective AI-content detector, this mismatch can mislead users into overtrusting the scientific basis and precision of results, which is a security-relevant integrity issue even though it does not enable code execution.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 87% confidence
Finding: The natural-language description presents the skill as inherently bilingual in Chinese and English, and the usage example also hardcodes bilingual text. This can violate language/locale policy expectations when a skill imposes a specific language format without offering the user a choice.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 89% confidence
Finding: This code sample presents its title, comments, sample text, and user-facing print output primarily in Chinese. Under the policy rule for natural-language violations, forcing a specific language without user opt-in can be a locale-policy issue, and this file does not indicate that Chinese output is optional or region-specific.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 90% confidence
Finding: This Python file includes natural-language descriptions that default to Chinese, such as the module docstring and many test/doc comments. Because the file does not indicate that the skill is region-specific or provide an English-only alternative for all user-facing text, it may conflict with a language/locale policy requiring opt-in or documented justification.
Content: No source excerpt is available for this finding.