ClawHub
Back to skill

Security audit

ponytail

Security checks for vulnerabilities and agentic risk

Overview

This is a Markdown-only coding-style skill that changes how the agent approaches coding tasks, with broad but disclosed session behavior and no evidence of malicious code, data access, or persistence on the system.

Install this if you want a persistent minimalist coding style during a session. Be ready to disable it with the documented phrases when you need normal behavior, expansive explanations, security-heavy analysis, or broader design exploration.

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 (2)

Vague Triggers

Medium
Confidence
89% confidence
Finding
The description says the skill applies to 'any coding task,' which is a very broad trigger with weak boundary conditions. In agent routing or auto-activation systems, this can cause the persona and output constraints to engage in contexts where the user did not clearly request them, potentially biasing coding, review, or security-sensitive tasks toward this mode.

Vague Triggers

Medium
Confidence
93% confidence
Finding
The skill explicitly declares itself active on every response and persistent until special disable phrases are used. That creates an over-broad behavioral override that can affect later requests without fresh user consent, increasing the chance the agent applies the skill outside the intended task and suppresses normal instruction-priority boundaries.

Static analysis

No suspicious patterns detected.