Back to skill

Security audit

ui-framework-spec

Security checks for vulnerabilities and agentic risk

Overview

This skill is a benign UI framework guidance pack with no evidence of hidden access, persistence, or data misuse.

Installers should treat this as a framework reference skill. Review generated code for the locale your project actually needs, since several examples show Chinese i18n imports, but the package does not request sensitive access or persistent changes.

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
  • Behavioral ASTexec() Call, eval() Call, Dynamic Import
  • 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 (4)

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

This manifest-like JSON file contains a prompt written entirely in Chinese, which can steer the skill toward a fixed language/locale behavior. The file does not indicate that language choice is optional or that Chinese is required for a region-specific purpose, so it may violate the policy against forcing a language without user opt-in.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
81% confidence
Finding

The markdown contains a concrete internationalization example that hard-codes the zh-cn locale. Because the document does not mention that locale selection should be user-driven or optional, it can encourage implementations that force a specific language without user opt-in.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

The note hard-codes use of the zh_CN locale in the internationalization example, which can be read as prescribing a specific language setting. Under the policy, locale-specific instructions should either offer alternatives or clearly justify why a fixed locale is required.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
89% confidence
Finding

Line L206 recommends importing zh_CN locale config for internationalization, which is a natural-language locale directive. Because the documentation presents a specific locale choice without mentioning user preference, alternatives, or opt-in, it can conflict with language/locale policy requirements.

Content

No source excerpt is available for this finding.