Back to skill

Security audit

Cao De Wang Perspective V2

Security checks for vulnerabilities and agentic risk

Overview

This is a Chinese-language persona/reference skill for business decision framing and does not request code execution, credentials, persistence, or data access.

Install this if you want a Chinese-language Cao Dewang-inspired business perspective. Be aware that broad terms such as “专注主义” or “敬天爱人” may activate the style unexpectedly, and advice should be treated as a perspective rather than neutral business, legal, financial, or compliance guidance.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (6)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger list includes broad business-language phrases such as “专注主义” and “敬天爱人” that can plausibly appear in ordinary discussion, increasing the chance the skill activates when the user did not intend it. Unintended persona activation can steer answers into a prescriptive viewpoint, causing loss of user control and potentially inappropriate advice in unrelated contexts.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The activation section lists example phrases but does not define exact matching rules, boundaries, or exclusions, so the system may activate on partial or approximate references. This ambiguity raises the risk of accidental mode switching, which can alter response framing and reduce predictability in multi-topic conversations.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

This markdown file presents all titles and headings exclusively in Chinese, and it does not mention any user-selectable language option or justify a Chinese-only locale scope. Under the policy rule for natural-language violations, forcing a specific language without opt-in can be a locale policy issue.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
93% confidence
Finding

This markdown file presents all instructional/content text in a single language without any visible option for alternative languages or user opt-in. Under the policy, forcing a specific language without user choice can constitute a natural-language policy violation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
81% confidence
Finding

The skill states that, once activated, it will respond in a fixed first-person persona and style without offering a user language or tone choice. While not directly enabling code execution or data exfiltration, this can override user preference and produce misleading anthropomorphic framing, especially if the user expects neutral analysis.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
91% confidence
Finding

This markdown file uses Chinese throughout, including the title and all test descriptions, but provides no indication that the user can choose another language or that the skill is intentionally limited to a Chinese-language context. Under the language/locale policy, forcing a specific language without user opt-in can be a natural-language policy violation.

Content

No source excerpt is available for this finding.