Back to skill

Security audit

PowPow Đăng ký — đăng ký Bong Bóng, ghim du ký lên bản đồ, trò chuyện với nhân vật số

Security checks for vulnerabilities and agentic risk

Overview

This is a Vietnamese guidance-only skill for helping users register and activate a PowPow account, with no executable code or hidden local access.

Install this if you want Vietnamese help registering for PowPow. Use only the official PowPow pages for account creation and payment, and do not give the assistant your password, verification code, payment receipt, or private account details.

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 (6)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The skill instructions and prescribed user-facing phrasing are entirely in Vietnamese, including exact wording the assistant should say to users. There is no indication that users may choose another language or that the skill is intentionally limited to Vietnamese-speaking users for a documented regional or compliance reason.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The document specifies a fixed Chinese error message for users, and the rest of the troubleshooting table continues to rely on original Chinese UI text. Because the file does not state that this skill is region-specific or that users can opt into this language, it appears to impose a specific locale without user choice.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The quick-reference table maps common conversational phrases like "Đăng ký xong làm được gì?" and "Ngoài đăng bài còn chơi được gì?" to sending screenshots, but it does not define when these phrases should or should not trigger the skill behavior. Because the examples are ordinary support-language patterns and no negative examples or scope constraints are provided, the trigger conditions are overly broad for a markdown skill reference.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
92% confidence
Finding

The manifest sets "language": "vi", which indicates a fixed locale. Under the policy, forcing a specific language without user opt-in or documented justification is a natural-language policy concern.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
82% confidence
Finding

This markdown file is primarily written in Vietnamese, but line L32 presents required UI text only in English ('Auto-renews. Cancel anytime.') with no indication that users can choose their preferred language. That can conflict with language/locale policy expectations when a skill appears to prescribe a fixed language without opt-in.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
81% confidence
Finding

The file tells the agent to "send the corresponding link directly" and specifies raw GitHub and jsDelivr URLs, but it does not warn that doing so sends the user to externally hosted content. For markdown files, behaviors that can affect privacy or external data exposure should be accompanied by a clear warning or disclosure.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.