Back to skill

Security audit

PowPow رجسٹریشن — بابل رجسٹر کرو، سفرنامیاں نوں نقشے تے پن کرو، ڈیجیٹل انساناں نال گل بات کرو

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed PowPow account registration and optional payment helper that handles sensitive signup data but keeps the behavior purpose-aligned and scoped to PowPow.

Install this only if you want an agent to help create a PowPow account. Expect to provide an email, password or generated password, verification code, and optionally an avatar; the helper will keep a temporary login token until cleanup. For payments, confirm the payment method yourself and complete payment only in the official Alipay or PayPal 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
  • 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
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Findings (27)

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 20)May include surrounding context.

md
- کور سکرپٹ `scripts/powpow-register.mjs`: **انحصار توں آزاد**، **Node >= 18** لوڑ اے۔ شروع کرن توں پہلے اک واری `node scripts/powpow-register.mjs status` چلاؤ

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 66)May include surrounding context.

md
- کور سکرپٹ `scripts/powpow-register.mjs`: **انحصار توں آزاد**، **Node >= 18** لوڑ اے۔ شروع کرن توں پہلے اک واری `node scripts/powpow-register.mjs status` چلاؤ

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 77)May include surrounding context.

md
- کور سکرپٹ `scripts/powpow-register.mjs`: **انحصار توں آزاد**، **Node >= 18** لوڑ اے۔ شروع کرن توں پہلے اک واری `node scripts/powpow-register.mjs status` چلاؤ

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 85)May include surrounding context.

md
- کور سکرپٹ `scripts/powpow-register.mjs`: **انحصار توں آزاد**، **Node >= 18** لوڑ اے۔ شروع کرن توں پہلے اک واری `node scripts/powpow-register.mjs status` چلاؤ

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 101)May include surrounding context.

md
- کور سکرپٹ `scripts/powpow-register.mjs`: **انحصار توں آزاد**، **Node >= 18** لوڑ اے۔ شروع کرن توں پہلے اک واری `node scripts/powpow-register.mjs status` چلاؤ

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 112)May include surrounding context.

md
- کور سکرپٹ `scripts/powpow-register.mjs`: **انحصار توں آزاد**، **Node >= 18** لوڑ اے۔ شروع کرن توں پہلے اک واری `node scripts/powpow-register.mjs status` چلاؤ

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 123)May include surrounding context.

md
- کور سکرپٹ `scripts/powpow-register.mjs`: **انحصار توں آزاد**، **Node >= 18** لوڑ اے۔ شروع کرن توں پہلے اک واری `node scripts/powpow-register.mjs status` چلاؤ

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 127)May include surrounding context.

md
- کور سکرپٹ `scripts/powpow-register.mjs`: **انحصار توں آزاد**، **Node >= 18** لوڑ اے۔ شروع کرن توں پہلے اک واری `node scripts/powpow-register.mjs status` چلاؤ

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 135)May include surrounding context.

md
- کور سکرپٹ `scripts/powpow-register.mjs`: **انحصار توں آزاد**، **Node >= 18** لوڑ اے۔ شروع کرن توں پہلے اک واری `node scripts/powpow-register.mjs status` چلاؤ

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 140)May include surrounding context.

md
- کور سکرپٹ `scripts/powpow-register.mjs`: **انحصار توں آزاد**، **Node >= 18** لوڑ اے۔ شروع کرن توں پہلے اک واری `node scripts/powpow-register.mjs status` چلاؤ

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The skill description is written as a fixed language presentation and does not indicate that users may choose another language or locale. Under the policy, forcing a specific language without user opt-in is a natural-language policy concern.

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 use of environment variables and outbound network access, but it declares no explicit tool scope or permissions. That creates a least-privilege failure: a host may grant broader capabilities than intended, making credential handling and external requests less auditable and easier to misuse.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
85% confidence
Finding

The skill metadata sets dir: rtl, and the entire skill is written to enforce a specific Punjabi/RTL interaction style, but there is no indication that users may choose another language or locale. Under the stated policy, forcing a language/locale without user opt-in is a natural-language policy violation unless clearly documented as region-specific or optional.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill directs the agent to invoke OS-specific commands like start/open/xdg-open on a locally generated payment page. Even if intended for convenience, this expands behavior from web registration assistance into host command execution, which can be abused if the generated path is untrusted, tampered with, or if the environment interprets the command unsafely.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The skill tells the agent to open a local payment page via system commands without explicit user notice or consent about local command execution. That weakens transparency and safe-operation expectations, and in combination with generated local files and payment flows could enable surprising or unsafe host-side actions.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The listing markets capabilities like pinning travel notes on maps and chatting with digital humans, which are outside the stated registration/login-only scope of this skill. Scope inflation is dangerous because it can cause users or orchestrators to invoke the skill in contexts where it may collect credentials or personal data under misleading expectations, increasing the chance of misuse and over-privileged activation.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
84% confidence
Finding

The metadata does not clearly constrain when the skill should activate, despite the skill handling sensitive flows such as registration, login, email verification, and optional payment/subscription steps. Without tight trigger scope, an agent platform may invoke the skill too broadly during unrelated conversations, creating unnecessary exposure of user identity, email, verification, or payment-related data.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The manifest sets the language to "pnb" while the file does not indicate that users can choose another language or that the locale restriction is required for a region-specific purpose. This creates a natural-language policy concern because it may enforce a language setting without user opt-in.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The skill is entirely written in a fixed non-default language/script and does not offer any language selection, fallback, or opt-in. In a security-sensitive workflow involving registration, login links, tokens, passwords, and payment steps, users who cannot read the content may misunderstand critical actions or be socially engineered into approving unsafe operations without informed consent.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
85% confidence
Finding

This markdown file is entirely written in Punjabi/Urdu-script language and does not indicate that users may choose another language or locale. Under the policy rule, forcing a specific language without opt-in is a natural-language policy violation unless the locale restriction is explicitly justified.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
87% confidence
Finding

The manifest says this skill handles optional membership upgrade payments via Alipay/PayPal and explicitly frames unsupported areas narrowly. This file documents additional WeChat QR and Huawei IAP subscription flows, including activation behavior, which are not justified by the manifest's declared purpose and supported channels.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The documentation acknowledges live legacy Alipay payment code remains in the codebase, including simulated-payment behavior when sandbox keys are absent, while asserting the skill never uses it. Dead-or-legacy payment paths with fake-success logic are dangerous because they can be accidentally reconnected, misrouted to, or abused to activate accounts or create inconsistent payment state without a real transaction.

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 markdown file presents all operational instructions in a single forced language/locale, with no opt-in, alternative language, or justification that the skill is region-specific.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The entire skill reference is written in Punjabi/Shahmukhi, and there is no indication that users can opt into another language or that the skill is intentionally limited to this locale. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The screenshot guidance expands the skill beyond its declared registration-only purpose by encouraging the agent to send promotional images for posting, maps, and digital-human features. In an autonomous agent context, this can cause scope creep, misleading users about what the skill does, and unintended actions or persuasion outside the authorized task flow.

Content

No source excerpt is available for this finding.