Back to skill

Security audit

深入浅出讲明白

Security checks for vulnerabilities and agentic risk

Overview

This is a Chinese writing-framework skill for producing structured explanatory articles, with no executable code or hidden system access.

Install this if you want a Chinese seven-step framework for clear explanatory articles. Specify your preferred output language and sources when invoking it, and treat the Ralph Wiggum example as sample prose rather than operational coding advice.

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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The skill name and description are entirely in Chinese and define the writing style for producing articles, but nowhere does the file indicate that language choice is optional or user-selected. This creates a natural-language locale constraint that appears to force a specific language without opt-in.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The content explicitly encourages unattended autonomous code modification and validation loops ('全程不需要人工干预', '等它自己把所有 bug 修好'), but does not warn about risks such as destructive edits, unsafe command execution, data loss, dependency changes, or system instability. In a skill intended to teach and promote developer workflow automation, this omission can normalize running high-impact code changes without human review, increasing the chance of integrity or availability issues.

Content

No source excerpt is available for this finding.