Security audit

ponytail

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed coding-style mode that pushes the assistant toward minimal implementations, with no executable code, data access, or hidden installation behavior.

Install this only if you want a persistent minimalist coding style. Turn it off with "stop ponytail" or "normal mode" when you need deeper design analysis, compliance review, broad architecture work, or intentionally fuller explanations.

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

High

Confidence: 96% confidence
Finding: The skill declares itself active for every response by default and persists until explicitly turned off, which makes it an always-on behavioral override rather than a narrowly scoped tool. This can silently steer unrelated tasks toward minimalistic outputs, suppress fuller reasoning or safer defaults, and create prompt-scope interference across the session.

Vague Triggers

Medium

Confidence: 91% confidence
Finding: The skill lacks a specific applicability boundary and instead describes a broad, persistent operating mode. Without concrete trigger scope and examples of when not to apply it, the assistant may invoke it in inappropriate contexts, including tasks needing completeness, nuance, or policy-sensitive handling.

Static analysis

No suspicious patterns detected.