ClawHub
Back to skill

Security audit

PerryTS — Native TypeScript Compiler

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-style PerryTS compiler skill whose installation, compiler, UI testing, and tooling guidance is disclosed and aligned with its stated purpose.

Install only if you intend to use PerryTS and are comfortable installing a native compiler/toolchain. Enable Geisterhand only during local development or testing, since it exposes a localhost interface that can inspect and drive the app under test.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Rogue AgentSelf-Modification, Session Persistence
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Self-Modification

High
Category
Rogue Agent
Confidence
90% confidence
Finding

Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.

Content

Scanner excerpt · SKILL.md (reported line 21)May include surrounding context.

brew install perryts/perry/perry # macOS winget install PerryTS.Perry # Windows perry doctor; perry --version # Verify perry update # Self-update

text

Prerequisites: macOS `xcode-select --install` / Linux `apt install build-essential` / Windows `winget install LLVM.LLVM && perry setup windows`

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
90% confidence
Finding

The Geisterhand section documents enabling an HTTP control server that can inspect widgets and drive UI actions, but it does not warn users that this exposes a local automation interface with powerful capabilities. Even though it binds to 127.0.0.1, local processes, browser-based localhost attacks, or misconfiguration/port forwarding could let untrusted code interact with the app during testing.

Content

No source excerpt is available for this finding.