Security audit

Agorism in the 21st Century Vol. 2

Security checks for vulnerabilities and agentic risk

Overview

This is a markdown-only philosophy and reference skill with no executable behavior, but users should apply its privacy and deletion ideas with legal and records-retention judgment.

Install this as a philosophical reference, not as operational compliance guidance. Treat its advice about opacity, privacy, and deletion as ideas to evaluate with applicable law, consent, auditability, and retention obligations before acting on them.

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 (2)

Missing User Warnings

Medium

Confidence: 93% confidence
Finding: The chapter explicitly frames deletion and even 'read the books and burn them' as a moral practice, but provides no contextual warning that irreversible destruction of records, evidence, safety documentation, or shared knowledge can cause real-world harm. In a knowledge skill that may be operationalized by downstream agents or users, this can normalize destructive behavior and record tampering under a philosophical banner.

Missing User Warnings

Low

Confidence: 82% confidence
Finding: The mental model tells users to evaluate data-collection through 'illumination or endarkenment' and treats concealment as legitimate, but omits boundaries around lawful privacy practices, consent, auditability, and misuse. In this skill's agorist/lunarpunk context, that framing could be interpreted as endorsing covert collection, concealment of actions, or evasion of oversight without balancing safeguards.

Static analysis

No suspicious patterns detected.