Back to skill

Security audit

Peng Lei Perspective V2

Security checks for vulnerabilities and agentic risk

Overview

This is a Chinese-language persona guidance skill for business and leadership advice, with no executable code or privileged behavior.

Install this if you want a Chinese-language leadership and business-advice persona. Be aware it may activate on broad business topics, so users who only want explicit persona switching may prefer narrower trigger wording.

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 (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The skill’s activation rules include broad, common business terms like “组织文化”, “人才发展”, and “用户洞察”, which are likely to appear in ordinary conversation without the user intending to invoke this persona. That can cause unintended activation and steer responses into a fixed perspective, reducing user control and potentially overriding safer or more appropriate default behavior for unrelated requests.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
79% confidence
Finding

The entire skill is written to operate in Chinese and its expression guidance is fixed to that language and style, but there is no statement offering the user a language choice or making the locale constraint explicit. Under the 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.