Security audit

PUA Breakthrough Mode

Security checks for vulnerabilities and agentic risk

Overview

This is a prompt-only workflow skill that encourages more persistent, evidence-based task execution without adding code, persistence, credential access, or hidden actions.

Install this if you want an agent workflow that pushes harder on complex tasks. Be aware that it may make agents more proactive and persistent, so use caution for high-stakes medical, legal, financial, or underspecified tasks where extra action without clarification could be inappropriate.

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 (1)

Vague Triggers

Medium

Confidence: 90% confidence
Finding: The description says to use the skill for broad situations like 'coding, debugging, research, planning, analysis, and other multi-step tasks' and for feelings such as when the agent seems 'too quick to conclude.' This leaves activation scope very open-ended and likely to collide with many ordinary tasks without clear boundaries or exclusion conditions.

Static analysis

No suspicious patterns detected.