Back to skill

Security audit

PowPow ਰਜਿਸਟਰੇਸ਼ਨ — ਬੁਲਬੁਲਾ ਰਜਿਸਟਰ ਕਰੋ, ਯਾਤਰਾ ਬਿਰਤਾਂਤਾਂ ਨੂੰ ਨਕਸ਼ੇ ਉੱਤੇ ਪਿੰਨ ਕਰੋ, ਡਿਜਿਟਲ ਇਨਸਾਨਾਂ ਨਾਲ ਗੱਲ ਕਰੋ

Security checks for vulnerabilities and agentic risk

Overview

The skill is a disclosed PowPow account-registration helper with optional subscription checkout support, and the inspected artifacts do not show hidden exfiltration, persistence, or unauthorized payment behavior.

Install only if you are comfortable letting the agent help create a PowPow account, send an email verification code, optionally upload an avatar, keep a temporary session token/order state, open an Alipay or PayPal checkout page, and poll payment status. Complete any payment yourself in the official cashier page, and run the cleanup step when finished.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (21)

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
- ਮੁੱਖ ਸਕ੍ਰਿਪਟ `scripts/powpow-register.mjs`: **ਜ਼ੀਰੋ-ਡਿਪੈਂਡੈਂਸੀ**, **Node ≥ 18** ਚਾਹੀਦਾ। ਸ਼ੁਰੂ ਕਰਨ ਤੋਂ ਪਹਿਲਾਂ ਇੱਕ ਵਾਰ `node scripts/powpow-register.mjs status`

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
- ਮੁੱਖ ਸਕ੍ਰਿਪਟ `scripts/powpow-register.mjs`: **ਜ਼ੀਰੋ-ਡਿਪੈਂਡੈਂਸੀ**, **Node ≥ 18** ਚਾਹੀਦਾ। ਸ਼ੁਰੂ ਕਰਨ ਤੋਂ ਪਹਿਲਾਂ ਇੱਕ ਵਾਰ `node scripts/powpow-register.mjs status`

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
- ਮੁੱਖ ਸਕ੍ਰਿਪਟ `scripts/powpow-register.mjs`: **ਜ਼ੀਰੋ-ਡਿਪੈਂਡੈਂਸੀ**, **Node ≥ 18** ਚਾਹੀਦਾ। ਸ਼ੁਰੂ ਕਰਨ ਤੋਂ ਪਹਿਲਾਂ ਇੱਕ ਵਾਰ `node scripts/powpow-register.mjs status`

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
- ਮੁੱਖ ਸਕ੍ਰਿਪਟ `scripts/powpow-register.mjs`: **ਜ਼ੀਰੋ-ਡਿਪੈਂਡੈਂਸੀ**, **Node ≥ 18** ਚਾਹੀਦਾ। ਸ਼ੁਰੂ ਕਰਨ ਤੋਂ ਪਹਿਲਾਂ ਇੱਕ ਵਾਰ `node scripts/powpow-register.mjs status`

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
- ਮੁੱਖ ਸਕ੍ਰਿਪਟ `scripts/powpow-register.mjs`: **ਜ਼ੀਰੋ-ਡਿਪੈਂਡੈਂਸੀ**, **Node ≥ 18** ਚਾਹੀਦਾ। ਸ਼ੁਰੂ ਕਰਨ ਤੋਂ ਪਹਿਲਾਂ ਇੱਕ ਵਾਰ `node scripts/powpow-register.mjs status`

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
- ਮੁੱਖ ਸਕ੍ਰਿਪਟ `scripts/powpow-register.mjs`: **ਜ਼ੀਰੋ-ਡਿਪੈਂਡੈਂਸੀ**, **Node ≥ 18** ਚਾਹੀਦਾ। ਸ਼ੁਰੂ ਕਰਨ ਤੋਂ ਪਹਿਲਾਂ ਇੱਕ ਵਾਰ `node scripts/powpow-register.mjs status`

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
- ਮੁੱਖ ਸਕ੍ਰਿਪਟ `scripts/powpow-register.mjs`: **ਜ਼ੀਰੋ-ਡਿਪੈਂਡੈਂਸੀ**, **Node ≥ 18** ਚਾਹੀਦਾ। ਸ਼ੁਰੂ ਕਰਨ ਤੋਂ ਪਹਿਲਾਂ ਇੱਕ ਵਾਰ `node scripts/powpow-register.mjs status`

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
- ਮੁੱਖ ਸਕ੍ਰਿਪਟ `scripts/powpow-register.mjs`: **ਜ਼ੀਰੋ-ਡਿਪੈਂਡੈਂਸੀ**, **Node ≥ 18** ਚਾਹੀਦਾ। ਸ਼ੁਰੂ ਕਰਨ ਤੋਂ ਪਹਿਲਾਂ ਇੱਕ ਵਾਰ `node scripts/powpow-register.mjs status`

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
- ਮੁੱਖ ਸਕ੍ਰਿਪਟ `scripts/powpow-register.mjs`: **ਜ਼ੀਰੋ-ਡਿਪੈਂਡੈਂਸੀ**, **Node ≥ 18** ਚਾਹੀਦਾ। ਸ਼ੁਰੂ ਕਰਨ ਤੋਂ ਪਹਿਲਾਂ ਇੱਕ ਵਾਰ `node scripts/powpow-register.mjs status`

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
- ਮੁੱਖ ਸਕ੍ਰਿਪਟ `scripts/powpow-register.mjs`: **ਜ਼ੀਰੋ-ਡਿਪੈਂਡੈਂਸੀ**, **Node ≥ 18** ਚਾਹੀਦਾ। ਸ਼ੁਰੂ ਕਰਨ ਤੋਂ ਪਹਿਲਾਂ ਇੱਕ ਵਾਰ `node scripts/powpow-register.mjs status`

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
- ਮੁੱਖ ਸਕ੍ਰਿਪਟ `scripts/powpow-register.mjs`: **ਜ਼ੀਰੋ-ਡਿਪੈਂਡੈਂਸੀ**, **Node ≥ 18** ਚਾਹੀਦਾ। ਸ਼ੁਰੂ ਕਰਨ ਤੋਂ ਪਹਿਲਾਂ ਇੱਕ ਵਾਰ `node scripts/powpow-register.mjs status`

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The file's natural-language instructions and descriptions are written entirely in Punjabi, and there is no indication that users may choose another language or that the skill is intentionally limited to Punjabi-speaking users. Under the policy, forcing a specific language without user opt-in is a locale/language policy violation.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill directs the agent to create payment orders, open local payment pages via system commands, and poll order status, but it does not require an explicit user confirmation immediately before launching the cashier flow or before continuous payment-status checking. In a conversational agent context, initiating browser/payment actions without a just-in-time warning can surprise users, create consent ambiguity, and normalize opaque payment handling around financial operations.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
82% confidence
Finding

The file is written entirely in Punjabi and instructs the agent to maintain a fixed PowPow service tone, but it does not offer the user a choice of language or explain that the skill is limited to a specific locale. Under the policy, forcing a language or locale without user 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
95% confidence
Finding

The manifest hard-codes the skill language to Punjabi ("pa") while other visible text in the file includes Chinese, and there is no indication that users can opt into or change the locale. This can violate language/locale policy when a specific language is imposed without user choice or a documented regional justification.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The manifest notes describe agent-driven capabilities such as sending codes, registration, and ordering on the user's behalf, but they do not define clear activation boundaries, approval gates, or scope limits. In a skill that performs external actions against third-party services, vague trigger conditions increase the risk of unintended account actions, purchases, or workflow escalation if the agent is invoked in the wrong context.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

SQP-3 applies to all file types and covers language or locale policy violations. This markdown file consistently mandates a specific language presentation, including mixed Punjabi and Chinese user-facing wording, but does not provide opt-in, alternatives, or a documented region-specific justification.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

This file imposes a specific language/locale in its natural-language instructions and embedded UI references, but does not indicate that the skill is region-specific or that users may choose another language. Under the stated policy, forcing a language without 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
90% confidence
Finding

This markdown file presents all operational instructions in Punjabi, but it does not state that the skill is region-specific or provide any user opt-in for the language/locale. Under the policy, forcing a specific language without user choice 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
93% confidence
Finding

The entire skill guidance is written in Punjabi and provides no indication that language choice is optional or limited to a region-specific deployment. Under the policy rule, forcing a specific language or locale 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
93% confidence
Finding

The file's user-facing documentation and command output strings are written entirely in Chinese, including usage, errors, and status messages. Under the stated policy, forcing a specific language without user opt-in is a natural-language policy violation unless the locale restriction is explicitly justified, which is not present here.

Content

No source excerpt is available for this finding.