ClawHub
Back to skill

Security audit

ponytail-help

Security checks for vulnerabilities and agentic risk

Overview

This skill displays a help card; its configuration commands are examples, and it explicitly prohibits making changes or saving state.

Invoking this skill should only display help. Configuration examples and update commands are optional actions; this review does not establish the safety of the broader Ponytail plugin.

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
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • 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)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The code configures an environment variable rather than displaying the declared quick reference. This is a materially different action, not a supporting implementation detail of the advertised display functionality.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.