Back to skill

Security audit

Ai Chat Enhancer 0f5a92

Security checks for vulnerabilities and agentic risk

Overview

This is a simple markdown-only Chinese tutorial skill with no executable code, but users should be cautious about any third-party model-access or sharing workflow it recommends.

Before using this skill, treat any Chat2API or similar deployment advice as third-party integration guidance: use legitimate provider access, avoid sharing account tokens or sessions, and consider privacy and provider policy implications for prompts and model traffic.

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
  • 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)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill promotes using Chat2API to access mainstream models at 'zero cost' and to share access with friends or colleagues, but provides no warning about account, credential, policy, privacy, or third-party service risks. In this context, omission of safety guidance is dangerous because users may expose API tokens, proxy unauthorized access, or mishandle sensitive prompts and data through an external access layer.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The trigger phrases include generic terms such as "Windows部署教程" and broad help requests, which can cause the skill to activate for ordinary user queries unrelated to the intended tool. This increases the chance of unintended invocation and can route users into guidance about third-party AI access/sharing workflows without clear consent or context.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

The file's description, steps, and trigger scenarios are entirely in Chinese, which effectively forces a specific language for interaction. The skill does not offer an alternative language option or explain that it is intentionally limited to Chinese-speaking users or a Chinese-language context.

Content

No source excerpt is available for this finding.