Security audit

Non-Consensus Thinking

Security checks for vulnerabilities and agentic risk

Overview

This is a markdown-only thinking framework for auditing contrarian decisions, with no evidence of code execution, credential access, persistence, or hidden behavior.

Before installing, consider that this skill may encourage rigorous source-checking and decision journaling, and one aphorism is untranslated. It should not need credentials, shell access, persistent memory, or permission to modify files unless you separately ask the agent to record outputs.

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

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 (1)

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 96% confidence
Finding: Line L081 inserts a Chinese phrase as a numbered instruction without offering translation, language choice, or user opt-in. This can violate language/locale policy because the skill implicitly requires comprehension of a specific language in its natural-language guidance.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.