Back to skill

Security audit

sample-customer-q2-faq

Security checks for vulnerabilities and agentic risk

Overview

This is a self-contained Chinese-language demo FAQ skill for desensitized business-analysis questions, with no executable code or hidden access behavior.

This appears safe to install as a demo FAQ/template. Users should be aware that the materials are primarily Chinese-language and should keep any real customer financial, route, or commercial details in private/internal repositories with a separate desensitization review.

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

Low
Category
Not specified by scanner
Confidence
91% confidence
Finding

This markdown file presents all substantive contact information and project description in Chinese, with no indication that users may request another language or that the skill is intentionally limited to a Chinese-speaking audience. Under the natural-language policy rule, forcing a specific language without user opt-in is a policy concern.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
92% confidence
Finding

This markdown file uses Chinese throughout the test descriptions and requirements, which effectively forces a specific language for users or reviewers interacting with the skill materials. The policy allows locale-specific content only when the constraint is explicitly justified or when users are given a language choice, neither of which is stated here.

Content

No source excerpt is available for this finding.