Back to skill

Security audit

射频领域客户项目技术支持

Security checks for vulnerabilities and agentic risk

Overview

This is a Chinese-language RF customer support playbook with no executable code, hidden behavior, or automatic access to user data.

Before installing, treat this as a procedural RF customer-support guide. If you use the case-library templates, avoid storing unnecessary customer-identifying details, mask sensitive project information where possible, and keep records under your organization's access-control, retention, and confidentiality rules.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill description is written as a Chinese-only invocation/behavior statement and does not indicate that the user may choose another language. Under the policy, forcing a specific language without user opt-in is a natural-language locale violation unless the constraint is explicitly justified.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill explicitly recommends building case repositories containing customer names, product models, application domains, and issue histories, but provides no minimization, consent, retention, or access-control guidance. In a customer-support workflow, this can lead to unnecessary collection and persistence of identifiable commercial data, increasing privacy, confidentiality, and contractual exposure if the data is mishandled or broadly shared.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.