Back to skill

Security audit

PowPow Rejestracja — zarejestruj się, przypnij dziennik podróży na mapie i rozmawiaj z cyfrowymi ludźmi

Security checks for vulnerabilities and agentic risk

Overview

This is a narrow informational registration guide for PowPow that does not run code, collect credentials, or perform payments for the user.

Install this if you want a Polish-language guide for creating and activating a PowPow account. The skill should not ask for your password, verification code, payment card, or other payment credentials; complete those steps only on the official PowPow, PayPal, WeChat, or Huawei interfaces.

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
  • 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 (7)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The README presents all user-facing guidance in Polish, including the skill description, features, and safety notes. For a general-purpose registration assistant, forcing a single language without opt-in can violate language/locale policy when no justification or alternative is provided.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The manifest description is entirely in Polish and defines the skill behavior and trigger phrases only in Polish, aside from one English phrase. Under the policy rules, forcing a specific language without user opt-in is a natural-language policy concern unless the locale restriction is clearly documented and justified, which is not present here.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The conversation UX and hard-rule sections prescribe how the assistant should speak, but they do so only in Polish and never state that the user may choose another language. This creates a language-policy issue because the skill appears to enforce a single language by default without explicit user choice or a documented regional justification.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The manifest sets the skill language to "pl", and the surrounding listing text does not indicate that users can choose another language or that the skill is intentionally limited to a Polish-specific audience. This is a natural-language locale policy concern because it hard-codes a language constraint without opt-in or documented justification.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The file is primarily written in Polish, but line L25 presents a login message in Chinese and describes it as the returned user-facing text. This indicates a fixed locale for end-user messaging without any indication of user choice, which is a natural-language locale policy concern.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

Lines L52-L64 list many user-visible errors in Chinese while the surrounding document is in Polish, suggesting the skill/system may force Chinese-language UI strings. Without an explicit opt-in or justification for a Chinese-only locale, this is a policy-relevant language constraint.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
84% confidence
Finding

This file’s operational instructions, examples, and usage guidance are entirely in Polish, which can effectively force a specific language for skill behavior. The policy allows locale constraints only when they are justified or when the user is given a language choice, neither of which is stated here.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.