Back to skill

Security audit

embedded-architecture-design

Security checks for vulnerabilities and agentic risk

Overview

This is a simple embedded-code migration checklist skill with no executable code, persistence, credential use, or hidden behavior.

Installers should understand this is a Chinese-language checklist/reporting aid for embedded code migration. Adding bilingual metadata and a narrower activation phrase would improve routing, but the current artifact does not show risky behavior.

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
91% confidence
Finding

The skill description '在将代码从一个平台迁移到另一个平台时使用' is broad and does not define clear activation triggers, exclusions, or scope boundaries. In an agent environment, overly broad activation can cause the skill to be invoked in inappropriate contexts, leading to irrelevant guidance, workflow confusion, or unintended handling of tasks outside embedded migration.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The description is written only in Chinese and does not declare a locale constraint or language fallback. In multilingual agent deployments, this can cause misrouting, incorrect invocation, or user misunderstanding, which weakens reliable skill selection and may result in the wrong workflow being applied.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.