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

The skill is a coherent PowPow registration helper, but it intentionally handles account credentials, email codes, login tokens, and optional payment links.

Install this only if you want an agent to complete PowPow registration for you. Use a PowPow-specific password, do not share mailbox or payment-account access, confirm PayPal auto-renewal before authorizing it, run cleanup when finished, and delete any temporary checkout HTML files after payment.

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 Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (22)

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
- Skrypt główny `scripts/powpow-register.mjs`: **zero zależności**, wymaga **Node ≥ 18**. Przed startem uruchom raz `node scripts/powpow-register.mjs status`, ż

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
- Skrypt główny `scripts/powpow-register.mjs`: **zero zależności**, wymaga **Node ≥ 18**. Przed startem uruchom raz `node scripts/powpow-register.mjs status`, ż

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
- Skrypt główny `scripts/powpow-register.mjs`: **zero zależności**, wymaga **Node ≥ 18**. Przed startem uruchom raz `node scripts/powpow-register.mjs status`, ż

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
- Skrypt główny `scripts/powpow-register.mjs`: **zero zależności**, wymaga **Node ≥ 18**. Przed startem uruchom raz `node scripts/powpow-register.mjs status`, ż

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
- Skrypt główny `scripts/powpow-register.mjs`: **zero zależności**, wymaga **Node ≥ 18**. Przed startem uruchom raz `node scripts/powpow-register.mjs status`, ż

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
- Skrypt główny `scripts/powpow-register.mjs`: **zero zależności**, wymaga **Node ≥ 18**. Przed startem uruchom raz `node scripts/powpow-register.mjs status`, ż

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
- Skrypt główny `scripts/powpow-register.mjs`: **zero zależności**, wymaga **Node ≥ 18**. Przed startem uruchom raz `node scripts/powpow-register.mjs status`, ż

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
- Skrypt główny `scripts/powpow-register.mjs`: **zero zależności**, wymaga **Node ≥ 18**. Przed startem uruchom raz `node scripts/powpow-register.mjs status`, ż

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
- Skrypt główny `scripts/powpow-register.mjs`: **zero zależności**, wymaga **Node ≥ 18**. Przed startem uruchom raz `node scripts/powpow-register.mjs status`, ż

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
- Skrypt główny `scripts/powpow-register.mjs`: **zero zależności**, wymaga **Node ≥ 18**. Przed startem uruchom raz `node scripts/powpow-register.mjs status`, ż

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
- Skrypt główny `scripts/powpow-register.mjs`: **zero zależności**, wymaga **Node ≥ 18**. Przed startem uruchom raz `node scripts/powpow-register.mjs status`, ż

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill description is entirely in Polish and presents the assistant as a Polish-language registration assistant, with no indication that users may choose another language or locale. Under the policy, forcing a specific language without opt-in is a natural-language policy violation unless the locale restriction is clearly justified.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill is explicitly designed to collect and relay sensitive registration data, handle passwords, process email verification codes, create login links, and initiate subscription payment flows on the user's behalf inside the conversation. Although it includes some operational safeguards, it lacks a clear user-facing consent, privacy disclosure, and security warning before collecting credentials and performing account/payment actions, which creates significant phishing, credential-handling, and unauthorized-action risk.

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 sets the skill language to "pl" with no indication that users can opt into another language or that the skill is intentionally limited to a Polish-only region or audience. Under the stated policy, forcing a specific language without user opt-in is 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
96% confidence
Finding

The guidance says to keep the same tone and always end each turn with a Polish-language block labeled „następny krok”. This imposes a specific language/locale convention in the interaction text without any opt-in or alternative language choice for the user.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The skill explicitly authorizes the agent to create payment orders and monitor payment status for both Alipay and auto-renewing PayPal subscriptions, but it does not require an explicit user confirmation step immediately before initiating a charge flow. For PayPal especially, this can lead to accidental enrollment in recurring billing if the agent proceeds based on ambiguous user intent, making unauthorized or unintended subscription activation more likely.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

This markdown file contains user-facing operational guidance exclusively in Polish, and there is no indication that the skill supports user language selection or that Polish is a required regional constraint. The policy calls for flagging language or locale restrictions when a specific language is effectively forced without user opt-in.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The guidance tells the agent to send screenshots whenever the user 'doesn't know' the product or needs to 'see' it, which is a broad trigger that can cause unnecessary file sharing without a precise user request. In a skill context, this can lead to oversharing bundled assets or revealing interface details more aggressively than intended, even if the content itself is not highly sensitive.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The file directs the agent to send local images and, if missing, fetch externally hosted copies from GitHub/jsDelivr without requiring disclosure or confirmation. That creates a real risk of unintended external network access, metadata leakage, and silent transmission to third-party infrastructure, which is especially problematic in restricted or privacy-sensitive environments.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The script claims cleanup removes session credentials, but it also creates payment checkout artifacts in temporary directories that persist after cleanup. Those files can contain sensitive authorization material, including an embedded bearer-style login token in the generated login link flow or a live PayPal approval URL, allowing another local user or process with temp-directory access to reuse the session or continue payment actions.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
86% confidence
Finding

The skill description and operational instructions are written as if the interaction will occur in Polish, but there is no statement that the user may choose another language. Under the policy, forcing a specific language or locale without opt-in 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
92% confidence
Finding

The document contains fixed English phrases such as “Auto-renews”, “Cancel anytime.”, and “You're All Set!” inside an otherwise Polish-language skill description. This indicates a language/locale constraint in user-facing text without any documented user opt-in or language-selection behavior.

Content

No source excerpt is available for this finding.