Security audit

Contradiction Analysis

Security checks for vulnerabilities and agentic risk

Overview

This is a text-only reasoning skill for structuring complex problems, with no evidence of hidden execution, data access, persistence, or exfiltration.

Install this if you want a Chinese-first, Mao contradiction-theory style framework for analyzing tradeoffs and priorities. Be aware it may be invoked for many broad 'complex problem' situations and may steer answers into that analytical framing unless you ask for another method or language.

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 (5)

Vague Triggers

Medium

Confidence: 90% confidence
Finding: The trigger condition is broad enough to activate on many ordinary 'complex problem' scenarios, which can cause the agent to invoke this skill too often and steer responses into an ideologically framed workflow rather than the most appropriate task-specific method. In an agent system, over-broad routing logic is dangerous because it can hijack decision-making, crowd out safer or more relevant skills, and create unreliable behavior across unrelated contexts.

Natural-Language Policy Violations

Medium

Confidence: 97% confidence
Finding: The manifest description and the body of the prompt are entirely written as directives for Chinese-language use, with no indication that the user may choose another language. Under the policy, forcing a specific language without opt-in is a natural-language locale violation unless the constraint is explicitly justified.

Natural-Language Policy Violations

Medium

Confidence: 88% confidence
Finding: The file’s description and all user-facing content are entirely in Chinese, with no indication that the skill supports other languages or that use of Chinese is optional. Under the stated policy, a skill that imposes a language/locale without opt-in can be a natural-language policy violation unless the constraint is explicitly justified.

Natural-Language Policy Violations

Low

Confidence: 77% confidence
Finding: The file presents a Chinese-language trigger directive ("触发：…时调用") as an instruction for invocation behavior, while the rest of the file is mixed-language. This may create a locale-specific usage expectation without explicitly stating that users may interact in their preferred language or that the Chinese-first framing is intentional and justified.

Natural-Language Policy Violations

Low

Confidence: 89% confidence
Finding: The manifest description is written entirely in Chinese, and the file content also assumes Chinese-language use. For a general-reference skill, this can be a language/locale policy violation if the skill does not offer user opt-in or explain that it is intentionally region- or language-specific.

Static analysis

No suspicious patterns detected.