Back to skill

Security audit

Cultural Intelligence Builder

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent cultural-awareness coaching aid with no evidence of hidden access, persistence, data exfiltration, or unsafe execution.

Installers should treat this as educational self-reflection support, not professional, legal, medical, or HR advice. The main practical caveats are the broad activation phrase and mixed English/Chinese documentation, not hidden technical 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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
Findings (3)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill description is written in Chinese and presents the capability as default behavior in that language, while later example prompts mix English and Chinese without stating that users may choose their preferred language. Under the policy, language or locale constraints should be opt-in or explicitly justified as region-specific.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
81% confidence
Finding

The document is predominantly in English, but this section switches to Chinese and presents a localized use case without any explicit user opt-in or note that multilingual examples are intentional. That can create a language/locale policy concern because the skill appears to assume or impose a specific language in part of its guidance.

Content

No source excerpt is available for this finding.

Vague Triggers

Low
Category
Not specified by scanner
Confidence
90% confidence
Finding

The trigger phrase "work with people from different cultures" is a broad natural-language description rather than a specific invocation. Users may say this in ordinary discussion, which could cause unintended activation because the manifest provides no narrowing context or exclusion conditions.

Content

No source excerpt is available for this finding.