ClawHub
Back to skill

Security audit

ponytail

Security checks for vulnerabilities and agentic risk

Overview

This skill provides coding guidance for the current session, with clear stop controls and no bundled executable code or sensitive-access instructions.

Expect this coding style to remain active throughout the session. Say "stop ponytail" or "normal mode" to disable it, and review generated code changes before applying 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
  • 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)

The activation description covers any coding task without requiring an explicit request to enable Ponytail mode.

Medium
Category
Trigger Abuse
Confidence
90% confidence
Finding

The description makes ordinary coding requests eligible for this skill, while the session instructions specify how to stop or change its level but not when to activate it. This can unintentionally apply a persistent development mode when the user only requested routine coding assistance.

Content

No source excerpt is available for this finding.