Back to skill

Security audit

丁磊思维视角 v2.0

Security checks for vulnerabilities and agentic risk

Overview

This is a Chinese-language persona/reference skill with no code or data access; the main caveat is that broad trigger phrases may activate it unexpectedly.

Install this if you want a Chinese-language Ding Lei-style product strategy lens. Prefer invoking it explicitly by name, and be aware that generic Chinese business terms may activate it in conversations where you did not intend to use the persona.

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
  • 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (5)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The trigger list includes broad natural-language phrases such as '产品主义' and '兴趣驱动' that can plausibly appear in ordinary user requests, increasing the chance the skill activates unintentionally and steers responses into this persona without explicit user consent. In a persona skill, over-broad activation can cause context hijacking or unexpected behavioral changes, even though the content itself is not overtly malicious.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
89% confidence
Finding

This markdown file presents all user-facing content in a single language, Chinese, without offering an alternative language or indicating that the locale is intentionally limited. Under the stated 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.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
95% confidence
Finding

This markdown file uses Chinese throughout and does not indicate that the language is optional, user-selected, or required for a specific regional purpose. Under the policy, forcing a specific language without user opt-in is a natural-language policy concern.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
75% confidence
Finding

The skill is written entirely in Chinese and presents a strongly localized persona without any visible opt-in or fallback behavior for users operating in other languages. While not directly exploitable in a severe way, forced locale behavior can degrade user control and lead to confusing or undesired responses if the skill activates unexpectedly.

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 user-facing natural language in Chinese, including the main heading and section labels, without any indication that the user opted into that language or that the skill is region-specific. The policy for SQP-3 flags language or locale constraints when they are imposed without opt-in or documented justification.

Content

No source excerpt is available for this finding.