Back to skill

Security audit

ponytail-audit

Security checks for vulnerabilities and agentic risk

Overview

The skill gives coherent instructions for reviewing a repository and reporting problems without changing code or adding persistent access.

Specify a folder or package to narrow the review; otherwise, it covers the whole repository. Reports default to simple English. The skill proposes fixes but explicitly leaves code unchanged.

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
Vulnerability Patterns
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • 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 output instructions require English without user opt-in.

Low
Category
Output Handling
Confidence
92% confidence
Finding

The output section specifies “Very simple English” as the report language without offering a language choice or justifying an English-only constraint. Unlike a request for plain language, this explicitly names the natural language to use regardless of the user's preference.

Content

No source excerpt is available for this finding.