Back to skill

Security audit

PowPow ndhaptar — ndhaptar Gelembung, cethak cathetan lelungan ing peta, omongan karo manungsa digital

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-only registration guide for PowPow/Gelembung, with no code execution, credential collection, or hidden install behavior.

Before installing, confirm you want a Javanese-language PowPow registration helper and are comfortable receiving product links and screenshots hosted on public third-party services. Do not share passwords, verification codes, or payment proof with the assistant; the skill itself correctly says those actions stay in the browser or app.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (7)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The user-facing skill description and operational guidance are written in Javanese throughout, with no indication that other languages are supported or that this locale restriction is intentional. Under the policy, forcing a specific language without user opt-in can be a natural-language policy violation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

Line L14 sets the manifest language to "jv", and the listing text also uses Javanese prominently. In this file there is no indication that users can choose another language or that the locale restriction is justified, which matches the language/locale policy violation criteria.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

This file forces a specific language for operational guidance, which can violate language/locale policy when users are not given an opt-in or alternative. The content does not indicate that the skill is region-specific or that another language version is available.

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 includes a fixed Chinese error message as the expected login behavior, indicating the skill is tied to Mandarin user-facing output. There is no indication that users can choose their language or that the Chinese-only behavior is a justified region-specific requirement, which creates a language/locale policy concern.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The troubleshooting section explicitly treats Mandarin error strings as the primary reference text for multiple user flows. Because the file does not state that the skill is limited to a Chinese locale or offer any localization option, this is a natural-language locale-policy issue.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The entire skill reference is authored in a specific language/locale, and the file does not indicate that users or operators can choose another language. Under the policy rule, forcing a specific language without opt-in is a natural-language policy concern unless the locale constraint is clearly documented and justified.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
83% confidence
Finding

This markdown file tells the agent to send raw GitHub or jsDelivr image links directly and states the images can be sent out, but it does not warn that doing so will load content from third-party hosts. For markdown files, omission of a warning about behavior that can affect user privacy is in scope for missing user warnings.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.