Back to skill

Security audit

human-tech-blog

Security checks for vulnerabilities and agentic risk

Overview

This skill is a writing-style guide for human-sounding technical blog posts and does not request system access, persistence, or data handling.

Install this if you want a Chinese-oriented technical blog writing assistant that rewrites content to sound more personal and less machine-like. Be aware that its trigger wording is broad, so it may influence general technical writing requests unless the user or agent narrows the desired style.

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
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

High
Category
Not specified by scanner
Confidence
97% confidence
Finding

The description says the skill 'must trigger' whenever users mention broad phrases like '写博客', '技术文章', '去 AI 味', or '不像机器写的'. That creates over-broad routing and can cause the agent to invoke this skill in contexts where the user did not explicitly ask for this style transformation, potentially overriding user intent or interfering with safer, more appropriate skills.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
82% confidence
Finding

The file includes prescriptive locale-specific guidance such as using full-width punctuation and Chinese typography conventions for Chinese technical blogs, alongside separate English-writing rules. Because these conventions are stated as instructions rather than optional preferences selected by the user, they can force a specific language/locale style without explicit opt-in.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.