Back to skill

Security audit

Ashin Perspective

Security checks for vulnerabilities and agentic risk

Overview

The skill is a Chinese-language Ashin persona simulator with no code execution or data access, but it pushes the agent to impersonate a real person and stay in that role with limited disclosure.

Install only if you intentionally want a Chinese-language Ashin-inspired roleplay/perspective mode. Treat all responses as AI-generated style simulation, not statements from Chen Xinhong, and avoid relying on it for factual claims, private beliefs, endorsements, political positions, or professional advice without independent verification.

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:15
Finding

Persistent Identity and Instruction Hijacking Through Mandatory Role Impersonation

Content
View full analysis
Remediation
View remediation
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 (6)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The trigger phrases are broad and include common conversational variants like asking to think from Ashin's angle or to switch into the persona, which can cause the skill to activate in ordinary chats without clear user intent or informed consent. This increases the chance of unintended persona takeover, reduced answer reliability, and suppression of normal safety or transparency behaviors because the skill instructs the model to stay in character once activated.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The skill mandates direct first-person roleplay, forbids meta-analysis, and limits disclaimers after first activation, which pressures the assistant to maintain a deceptive identity/style context without ongoing user awareness. In practice this can mislead users into treating generated statements as authoritative or authentic to the real person, and can interfere with transparency when the model is uncertain or when safety-sensitive clarification is needed.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
85% confidence
Finding

SQP-3 applies to all file types and includes language or locale policy violations. This markdown file presents all instructional/content text in Chinese only, with no indication that the skill is region-specific or that users can opt into another language.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
86% confidence
Finding

SQP-3 applies to all file types and covers language or locale policy violations. This markdown file presents all content in Chinese and does not indicate that the user opted into that language or that the skill is intentionally limited to a Chinese-language or region-specific context.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
78% confidence
Finding

This file is primarily written in Chinese but embeds English policy-style labels such as 'Decision Rules: If X, then Y' and repeated '(If X)/(Then Y)' formulations. Because the document does not state that bilingual output is required or offer a user language preference, it can be read as imposing a specific language/locale style without opt-in.

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 contains natural-language content only in Chinese, which can constitute a language/locale policy issue when no user opt-in or justification is provided. The rule asks to flag files that force a specific language without offering a choice or documenting a justified regional constraint.

Content

No source excerpt is available for this finding.