ClawHub
Back to skill

Security audit

Ponytail

Security checks across malware telemetry and agentic risk

Overview

This is a prompt-only coding style skill that persistently nudges the agent toward minimal, practical code, with no executable behavior or hidden data access.

Install this only if you want a persistent minimalist coding style that favors small diffs, fewer abstractions, and concise explanations. Use 'stop ponytail' or 'normal mode' when you want fuller design exploration or a less opinionated coding approach.

SkillSpector

By NVIDIA
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

High
Confidence
96% confidence
Finding
The skill declares itself 'ACTIVE EVERY RESPONSE' with persistent behavior until an explicit opt-out, which makes it likely to influence unrelated coding interactions without a fresh user request. This can override user intent, suppress fuller analysis or explanation, and cause unintended behavior across a session even when the user did not mean to invoke this skill.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.