Back to skill

Security audit

Jing Xiandong Perspective V2

Security checks for vulnerabilities and agentic risk

Overview

This is a text-only business-perspective skill with no code, tools, persistence, or data access, though its broad triggers and first-person persona style deserve caution.

Install only if you want business advice framed through this named executive-style perspective. Treat first-person examples as roleplay, not factual personal testimony, and be aware that broad business prompts may activate the style even when you did not explicitly ask for it.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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
93% confidence
Finding

The activation rules include broad, generic business phrases such as compliance, IPO preparation, internationalization, crisis handling, ESG strategy, and succession planning. This can cause the skill to trigger in many unrelated conversations, overriding user expectations and increasing the chance of unintended persona steering or policy/style injection into normal assistant behavior.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
83% confidence
Finding

The skill strongly prescribes Chinese-language stylistic output and first-person persona phrasing without offering a user-language fallback. This can cause responses to ignore the user's preferred language or format, reducing reliability and potentially misleading users by implying direct personal experience or identity emulation.

Content

No source excerpt is available for this finding.