ClawHub
Back to skill

Security audit

token-kill

Security checks for vulnerabilities and agentic risk

Overview

This is a markdown-only cost-optimization guide with no bundled code, persistence, credential handling, or hidden execution behavior.

Before following the recommendations, choose models and script integrations that match your region, privacy requirements, provider availability, and data sensitivity. Treat /new, /compress, /stop, and /restart as deliberate user actions because they can affect context or current work.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
78% confidence
Finding

The markdown recommends fixed model selections including region/language-specific offerings such as Ernie, Qwen, and Tongyi as the default tiering strategy. Because the document does not present these as optional or dependent on user locale/preferences, it can be read as forcing a specific language/locale ecosystem without opt-in.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.