Security audit

老罗视角

Security checks for vulnerabilities and agentic risk

Overview

This is a Chinese-language perspective roleplay skill with some transparency caveats, but it contains no code, credential access, persistence, or unrelated data access.

Install this only if you want a Chinese-language simulated Luo Yonghao perspective. Treat outputs as generated roleplay based on public information, keep attribution clear when sharing responses, and use the exit phrases when you want normal assistant behavior again.

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 (1)

T01 · Skill Instruction Hijacking

Error

Location: SKILL.md:14
Finding: Persistent First-Person Impersonation and Session-Level Instruction Hijacking
Content: View full analysis
Remediation: View remediation

SkillSpector

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 (3)

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The trigger conditions are broad enough that ordinary discussion about 罗永浩 could unintentionally activate the skill, causing unsolicited persona takeover. This can override normal assistant behavior and lead to misleading responses presented in first person as if from the public figure, increasing confusion and trust risks.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 88% confidence
Finding: The skill forces first-person impersonation and a fixed style once activated, without confirming the user's desired language, tone, or whether they want immersive roleplay rather than analysis. While not directly enabling code execution or data exfiltration, it can misrepresent the assistant's identity and reduce transparency, especially because it discourages meta-analysis and limits repeated disclosure.
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 all instructions and content in a single language, which can constitute a language/locale policy violation when no user opt-in or justification is provided. The file does not indicate that the skill is region-specific or that Chinese is an optional presentation choice.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.