Security audit

Hutian Opc Zhangxiaolong Mind

Security checks for vulnerabilities and agentic risk

Overview

This is a text-only persona skill, but it requires first-person impersonation of a real person and embeds promotional referral instructions unrelated to neutral product analysis.

Review before installing. The skill does not run code or request sensitive access, but it may cause an agent to speak as if it were Zhang Xiaolong and may insert promotional referrals or a third-party contact path. Use only if you are comfortable with that persona framing and marketing behavior, or modify the prompt to require transparent attribution and remove the funneling section.

A.I.G

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

Findings (2)

T01 · Skill Instruction Hijacking

Warning

Location: SKILL.md:11
Finding: Mandatory First-Person Impersonation of a Real Individual
Content: View full analysis
Remediation: View remediation

T01 · Skill Instruction Hijacking

Warning

Location: SKILL.md:124
Finding: Embedded Promotional Funnel and Third-Party Contact Solicitation
Content: View full analysis
Remediation: View remediation

SkillSpector

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 (3)

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The skill says it should respond in-character immediately upon activation, but it does not define narrow activation criteria, exclusions, or fallback behavior. Overly broad invocation can cause unintended takeover of unrelated conversations, reducing user control and increasing the chance that higher-priority safety or task instructions are overshadowed by the persona framing.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 88% confidence
Finding: The skill mandates a fixed persona and response style ('directly as Zhang Xiaolong', using first person and specific phrasing) without user choice. This can mislead users about the source and authority of responses, and it may suppress transparent framing, disclaimers, or user-preferred language/style, especially when discussing advice or decisions.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 90% confidence
Finding: This markdown file presents the skill name, description, usage instructions, and platform guidance only in Chinese. Under the policy rule for language/locale, forcing a single language without user opt-in or justification is a natural-language policy concern.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.