Back to skill

Security audit

测试审核记录保存2

Security checks for vulnerabilities and agentic risk

Overview

This is a simple code-review guidance skill with no executable code, persistence, credential handling, or hidden behavior.

Install this if you want a Chinese-language structured code review checklist. Be aware it may be invoked broadly around task completion or submission unless your agent lets you narrow skill use.

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

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The description says the skill should be used 'before code submission or after task completion' for code review, which is a broad situational trigger rather than a specific invocation scope. It does not define clearer boundaries, explicit trigger phrases, or exclusion cases, so the skill may be invoked in many ordinary development contexts unintentionally.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
87% confidence
Finding

The natural-language content of the skill is entirely in Chinese, including the description and required output template, with no indication that the user may choose another language. This can violate language or locale policy when a skill imposes a specific language without opt-in or documented justification.

Content

No source excerpt is available for this finding.