Back to skill

Security audit

Pagrehistro ng PowPow — magrehistro ng Bula, i-pin ang talaarawan ng paglalakbay sa mapa, kausapin ang digital na tao

Security checks for vulnerabilities and agentic risk

Overview

The skill is mostly coherent for PowPow account registration, but its payment flow and session artifacts need human review before installation.

Install only if you are comfortable letting the agent run the bundled Node script, contact global.powpow.online, handle registration/session tokens, and create optional payment orders. Confirm each payment action yourself, verify the browser destination before paying, and remove any temporary powpow-pay checkout folders after use.

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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
Findings (24)

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 19)May include surrounding context.

md
- Pangunahing script `scripts/powpow-register.mjs`: **zero dependency**, nangangailangan ng **Node >= 18**. Bago magsimula, patakbuhin nang isang beses ang `nod

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 65)May include surrounding context.

md
- Pangunahing script `scripts/powpow-register.mjs`: **zero dependency**, nangangailangan ng **Node >= 18**. Bago magsimula, patakbuhin nang isang beses ang `nod

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 76)May include surrounding context.

md
- Pangunahing script `scripts/powpow-register.mjs`: **zero dependency**, nangangailangan ng **Node >= 18**. Bago magsimula, patakbuhin nang isang beses ang `nod

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 84)May include surrounding context.

md
- Pangunahing script `scripts/powpow-register.mjs`: **zero dependency**, nangangailangan ng **Node >= 18**. Bago magsimula, patakbuhin nang isang beses ang `nod

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 100)May include surrounding context.

md
- Pangunahing script `scripts/powpow-register.mjs`: **zero dependency**, nangangailangan ng **Node >= 18**. Bago magsimula, patakbuhin nang isang beses ang `nod

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 111)May include surrounding context.

md
- Pangunahing script `scripts/powpow-register.mjs`: **zero dependency**, nangangailangan ng **Node >= 18**. Bago magsimula, patakbuhin nang isang beses ang `nod

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 122)May include surrounding context.

md
- Pangunahing script `scripts/powpow-register.mjs`: **zero dependency**, nangangailangan ng **Node >= 18**. Bago magsimula, patakbuhin nang isang beses ang `nod

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 126)May include surrounding context.

md
- Pangunahing script `scripts/powpow-register.mjs`: **zero dependency**, nangangailangan ng **Node >= 18**. Bago magsimula, patakbuhin nang isang beses ang `nod

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 133)May include surrounding context.

md
- Pangunahing script `scripts/powpow-register.mjs`: **zero dependency**, nangangailangan ng **Node >= 18**. Bago magsimula, patakbuhin nang isang beses ang `nod

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 134)May include surrounding context.

md
- Pangunahing script `scripts/powpow-register.mjs`: **zero dependency**, nangangailangan ng **Node >= 18**. Bago magsimula, patakbuhin nang isang beses ang `nod

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 139)May include surrounding context.

md
- Pangunahing script `scripts/powpow-register.mjs`: **zero dependency**, nangangailangan ng **Node >= 18**. Bago magsimula, patakbuhin nang isang beses ang `nod

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
92% confidence
Finding

The skill documents operational capabilities that involve environment variables, network access, and external script execution, but it does not declare an explicit tool/permission scope in the manifest. This creates a least-privilege and review gap: a host may permit broader execution than users or auditors expect, especially because the skill handles credentials, email verification, and payment-related flows.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
84% confidence
Finding

The skill directs the agent to create payment orders, open payment pages, and poll for payment completion, but it does not present a strong, upfront warning and consent boundary before initiating those external financial actions. In a payment workflow, insufficient disclosure can cause users to be surprised by browser launches, order creation, or monitoring behavior, undermining informed consent and increasing phishing-like risk.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The skill instructs the agent to invoke OS-specific commands like start/open/xdg-open on a returned file path to launch a payment page. Even if the intended target is benign, opening local paths or shelling out based on generated output introduces a command-execution and unsafe-launch surface, especially in a payment context where redirection or path manipulation would be highly sensitive.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The documentation expands payment support beyond the stated channels by introducing WeChat QR and Huawei IAP handling in the procedural flow. Scope drift like this is dangerous because it encourages operators or agents to improvise unsupported financial workflows, increasing the chance of mishandling payment states, user expectations, or sensitive transaction-related data.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The listing metadata markets capabilities beyond the stated registration/login scope by referencing travel-map journaling and digital-human chat. This scope expansion can mislead users and reviewers about what the agent does, weakening informed consent and increasing the chance that a registration-focused skill is invoked in broader contexts with access to user identity, email verification, avatar upload, and possibly payment-related flows.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The manifest sets the language to "tl", and the visible display name and keywords are also localized to Tagalog. There is no indication that users can opt into another language or that the skill is intentionally limited to a Tagalog-speaking region for a documented reason, which matches the 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 entire skill file is written in Filipino/Tagalog and instructs the agent to use that language and keep the same tone, but it does not offer the user any language choice or opt-in. This is a natural-language policy concern because it imposes a locale/language behavior across the skill flow without documented justification or user selection.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

This markdown file includes user-facing guidance that relies on Chinese text such as 该账号未设置密码,请使用其他方式登录, and similar Chinese-only strings continue throughout the troubleshooting section. Under the policy rule for natural-language violations, forcing a specific language or locale without user opt-in can be problematic when the skill otherwise presents itself in another language.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
83% confidence
Finding

The file's operational instructions are entirely in Filipino/Tagalog, which can impose a language preference if this skill is used in broader contexts. There is no indication that the user can choose another language or that the locale restriction is intentional and justified.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The instruction says to use screenshots 'kung kailan kinakailangan sa oras ng pagtakbo' and when the user has 'walang idea' about the product, which is broad and subjective. It does not clearly define boundaries for when screenshots should or should not be sent, increasing the chance of unintended or inconsistent invocation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

Natural-language strings throughout the file, including the header comments, errors, status messages, and usage text, are exclusively in Chinese. Per the policy, forcing a specific language without user opt-in is a natural-language policy violation unless the locale constraint is explicitly documented and justified, which is not present here.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The header comment states that session tokens are removed on cleanup, but the script also writes checkout artifacts to temporary HTML files that can contain active payment approval URLs or login-related redirect links outside the tracked state file lifecycle. In this skill context, the agent is explicitly handling account creation, login, and payment flows on behalf of users, so leaving residual browser-openable artifacts in temp directories meaningfully increases the chance of session or payment-link reuse by other local users or later processes on the same machine.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
86% confidence
Finding

The natural-language instructions, prompts, and required UX phrasing are all specified in Filipino/Tagalog, including fixed response patterns in the conversation UX section. There is no indication that the user can opt into another language or that this locale restriction is required for a region-specific compliance purpose.

Content

No source excerpt is available for this finding.