Back to skill

Security audit

PowPow Registro — Regístrate en Burbuja, fija tu diario de viaje en el mapa, chatea con humanos digitales

Security checks for vulnerabilities and agentic risk

Overview

This skill performs a disclosed PowPow registration and optional subscription flow, with sensitive but purpose-aligned handling of account data and temporary session state.

Install only if you are comfortable letting the agent create a PowPow account for you, submit your registration details to global.powpow.online, and temporarily hold a session token while it completes login or optional subscription steps. Run the cleanup step when finished, and complete any Alipay or PayPal payment yourself in the official checkout page.

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
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
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
- Script principal `scripts/powpow-register.mjs`: **cero dependencias**, requiere **Node ≥ 18**. Antes de empezar, ejecuta una vez `node scripts/powpow-register

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
- Script principal `scripts/powpow-register.mjs`: **cero dependencias**, requiere **Node ≥ 18**. Antes de empezar, ejecuta una vez `node scripts/powpow-register

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
- Script principal `scripts/powpow-register.mjs`: **cero dependencias**, requiere **Node ≥ 18**. Antes de empezar, ejecuta una vez `node scripts/powpow-register

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
- Script principal `scripts/powpow-register.mjs`: **cero dependencias**, requiere **Node ≥ 18**. Antes de empezar, ejecuta una vez `node scripts/powpow-register

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
- Script principal `scripts/powpow-register.mjs`: **cero dependencias**, requiere **Node ≥ 18**. Antes de empezar, ejecuta una vez `node scripts/powpow-register

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
- Script principal `scripts/powpow-register.mjs`: **cero dependencias**, requiere **Node ≥ 18**. Antes de empezar, ejecuta una vez `node scripts/powpow-register

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
- Script principal `scripts/powpow-register.mjs`: **cero dependencias**, requiere **Node ≥ 18**. Antes de empezar, ejecuta una vez `node scripts/powpow-register

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
- Script principal `scripts/powpow-register.mjs`: **cero dependencias**, requiere **Node ≥ 18**. Antes de empezar, ejecuta una vez `node scripts/powpow-register

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
- Script principal `scripts/powpow-register.mjs`: **cero dependencias**, requiere **Node ≥ 18**. Antes de empezar, ejecuta una vez `node scripts/powpow-register

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
- Script principal `scripts/powpow-register.mjs`: **cero dependencias**, requiere **Node ≥ 18**. Antes de empezar, ejecuta una vez `node scripts/powpow-register

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
- Script principal `scripts/powpow-register.mjs`: **cero dependencias**, requiere **Node ≥ 18**. Antes de empezar, ejecuta una vez `node scripts/powpow-register

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

Todo el contenido visible del skill está redactado en español y no indica que el usuario pueda elegir otro idioma ni que el skill esté limitado a una región hispanohablante. Según la política indicada, forzar un idioma concreto sin opt-in o justificación clara constituye una violación de política lingüística.

Content

No source excerpt is available for this finding.

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
95% confidence
Finding

The skill clearly instructs the agent to use environment variables and make network requests to an external service, but it does not declare an explicit tool/permission scope. That creates a governance gap: an agent runtime may grant broader capabilities than reviewers or users expect, making sensitive registration data handling less transparent and harder to constrain.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill collects and transmits personal data including email, username, optional phone number, and avatar to a third-party service, but the description does not provide a clear upfront disclosure or consent checkpoint before data transfer. This is dangerous because users may not realize the agent is acting as an intermediary and sending their personal information off-platform.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

La sección de UX fija el tono de servicio habitual de PowPow y redacta instrucciones enteramente en español, sin ofrecer alternativa de idioma ni indicar que el usuario puede elegir lengua. Según la política, forzar un idioma o locale sin opt-in explícito constituye una violación de política lingüística.

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 explicitly sets the skill language to "es", while the rest of the listing includes mixed-language content and no indication that users can opt into another language or that the skill is region-specific. This is a natural-language locale constraint that may violate policy when imposed without user choice or clear justification.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

SQP-3 applies to all file types and covers language or locale policy violations. This file mandates a specific language presentation for the skill instructions and references mixed fixed-language user-facing text, but does not state that the skill is region-specific or that users can opt into their preferred language.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
87% confidence
Finding

This markdown file contains user-facing guidance that requires specific Chinese-language messages as part of the workflow, but it does not indicate that the user can choose another language or that the skill is limited to Chinese-speaking contexts. Under the locale policy, forcing a specific language without opt-in is a natural-language policy concern.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The troubleshooting section repeatedly instructs users to match exact Chinese error strings, which effectively assumes a fixed UI language. Because the file is otherwise written in Spanish and does not state that the platform or skill is intentionally Chinese-only, this creates a language policy issue.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

La frase "según haga falta en tiempo de ejecución" y el criterio "si el usuario no tiene ni idea... o necesita ver" no delimitan con precisión cuándo debe activarse el envío de imágenes. Esta redacción puede solaparse con muchas situaciones conversacionales comunes y provocar invocaciones no deseadas o inconsistentes.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The script persists the live session token to a predictable file in the system temporary directory (powpow-register-state.json). Although it uses mode 0o600, temporary directories are commonly accessible to local processes running as the same user, and the token is later turned into a one-click login URL, so theft of the file can enable account session hijacking until cleanup or token expiry. In this skill context, the risk is elevated because the agent is explicitly handling account registration and payment flows, making the stored token capable of accessing subscription and account actions.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

After re-authentication, the refreshed session token is again saved to the same local state file without an explicit runtime warning. This extends the window during which a valid authenticated token exists on disk, increasing exposure to local compromise or accidental leakage; because the token represents an updated post-payment session, it may grant broader access to an active subscription account.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
76% confidence
Finding

Todo el contenido instructivo fuerza un único idioma para la operación de la habilidad y no ofrece opt-in ni alternativa de idioma. Según la política indicada, imponer un idioma sin elección del usuario puede constituir una violación de política lingüística.

Content

No source excerpt is available for this finding.

Vague Triggers

Low
Category
Not specified by scanner
Confidence
81% confidence
Finding

El término "Apertura" es ambiguo porque no especifica si se refiere al inicio de cualquier conversación, a una demo guiada o a una consulta concreta del usuario. Sin restricciones adicionales, puede hacer que la habilidad envíe imágenes en contextos demasiado amplios.

Content

No source excerpt is available for this finding.