ClawHub
Back to skill

Security audit

张洪Heo博客助手 - HTTP API 搜索/热门/归档/标签/友链

Security checks for vulnerabilities and agentic risk

Overview

This skill is a public blog lookup helper with a minor chance of activating on overly broad trigger words.

Installers should understand that this skill may call blog.zhheo.com when blog-related prompts match its broad trigger words. Consider narrowing the triggers if accidental activation would be annoying, but the inspected artifact does not show credential access, persistence, local data collection, or unsafe actions.

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
  • 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 (2)

Vague Triggers

Medium
Confidence
97% confidence
Finding
The trigger list includes very broad everyday terms such as “博客”, “博主”, and especially “Heo”, which can unintentionally activate the skill in unrelated conversations. This can cause the agent to route user requests to this skill when the user did not intend to query this specific blog, leading to misfires, irrelevant external HTTP requests, and possible confusion or data exposure through unintended tool use.

Vague Triggers

Medium
Confidence
95% confidence
Finding
The markdown trigger section repeats ambiguous activation terms without any disambiguation guidance, increasing the chance of accidental invocation during ordinary discussion about blogs or a blogger. In this skill’s context, accidental activation is more concerning because invocation leads to outbound HTTP access and content retrieval from an external site, expanding the effect of a simple routing mistake.

Static analysis

No suspicious patterns detected.