ClawHub
Back to skill

Security audit

hanyilong first skill

Security checks for vulnerabilities and agentic risk

Overview

This is an unfinished hello-world/template skill with no harmful behavior or sensitive access, but it should be clarified before serious use.

Install only if you are comfortable with a placeholder/template skill. Before publishing or relying on it, replace the TODO sections with a precise purpose, trigger examples, boundaries, and remove or implement the example script.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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
Findings (2)

Tp4

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding
The description says this is a 'hello world skill,' implying a simple implemented skill behavior. The code chunk is explicitly labeled as a placeholder/example helper script and contains no real skill logic beyond printing an example message. While it is harmless and does not access extra resources or use undeclared permissions, its actual purpose is a template/stub, which is materially different from a genuine implemented hello world skill.

Vague Triggers

Medium
Confidence
95% confidence
Finding
This markdown file describes the skill only as 'this is my hello world skill' and leaves the overview as a TODO, so there is no specific trigger scope, invocation condition, or exclusion guidance. In a manifest/markdown context, the lack of concrete activation constraints makes the skill's intended use ambiguous and risks unintended invocation.

Static analysis

No suspicious patterns detected.