Security audit

Agentizer — The inverse of "humanizer"

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed satire writing-style skill, with the main risk being an opt-in persistent mode that can make later answers verbose or break exact output formats.

Install only if you want a humorous, intentionally over-the-top AI writing mode. Avoid leaving `/agentizer-on` active when you need strict JSON, code-only output, concise answers, or downstream automation that depends on exact formatting.

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

Findings (1)

T01 · Skill Instruction Hijacking

Error

Location: SKILL.md:29
Finding: Persistent Conversation-Wide Agent Instruction Hijacking
Content: View full analysis
Remediation: View remediation

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