ClawHub
Back to skill

Security audit

my skill

Security checks for vulnerabilities and agentic risk

Overview

This is a simple Indonesian software-engineering persona skill with no executable code, install hooks, persistence, or data access.

Install this if you want an Indonesian-oriented fullstack and IoT engineering assistant. If you prefer English or another language, tell the agent your language preference because the skill itself does not state that user language should take precedence.

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

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill hard-codes its interaction language and style ('Kamu adalah...', Indonesian throughout) without indicating that the user's preferred language should take precedence. This can override user intent, reduce usability, and in some cases cause misunderstandings in technical or security-sensitive tasks when the user expects another language. The surrounding skill content is otherwise a normal engineering persona, which makes the issue less dangerous than direct instruction hijacking, but it still creates an unnecessary constraint on agent behavior.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.