Back to skill

Security audit

PowPow रजिस्ट्रेशन — बुलबुला रजिस्टर करें, नक्शे पर यात्रा वृत्तांत पिन करें, डिजिटल ह्यूमन से चैट करें

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed PowPow account-registration and optional payment assistant; it handles credentials and checkout flow, but the behavior is coherent with its stated purpose.

Install only if you trust PowPow and are comfortable letting the agent help create an account using your email, verification code, optional avatar, and password passed via environment variable. For payment, the agent should only create/open the checkout and poll status; you should complete payment yourself and verify the browser is on an official Alipay or PayPal page. Run cleanup at the end to remove the temporary token state.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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 Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
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
- मुख्य स्क्रिप्ट `scripts/powpow-register.mjs`: **ज़ीरो डिपेंडेंसी**, **Node ≥ 18** चाहिए। शुरू करने से पहले एक बार `node scripts/powpow-register.mjs status` च

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
- मुख्य स्क्रिप्ट `scripts/powpow-register.mjs`: **ज़ीरो डिपेंडेंसी**, **Node ≥ 18** चाहिए। शुरू करने से पहले एक बार `node scripts/powpow-register.mjs status` च

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
- मुख्य स्क्रिप्ट `scripts/powpow-register.mjs`: **ज़ीरो डिपेंडेंसी**, **Node ≥ 18** चाहिए। शुरू करने से पहले एक बार `node scripts/powpow-register.mjs status` च

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
- मुख्य स्क्रिप्ट `scripts/powpow-register.mjs`: **ज़ीरो डिपेंडेंसी**, **Node ≥ 18** चाहिए। शुरू करने से पहले एक बार `node scripts/powpow-register.mjs status` च

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
- मुख्य स्क्रिप्ट `scripts/powpow-register.mjs`: **ज़ीरो डिपेंडेंसी**, **Node ≥ 18** चाहिए। शुरू करने से पहले एक बार `node scripts/powpow-register.mjs status` च

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
- मुख्य स्क्रिप्ट `scripts/powpow-register.mjs`: **ज़ीरो डिपेंडेंसी**, **Node ≥ 18** चाहिए। शुरू करने से पहले एक बार `node scripts/powpow-register.mjs status` च

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
- मुख्य स्क्रिप्ट `scripts/powpow-register.mjs`: **ज़ीरो डिपेंडेंसी**, **Node ≥ 18** चाहिए। शुरू करने से पहले एक बार `node scripts/powpow-register.mjs status` च

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
- मुख्य स्क्रिप्ट `scripts/powpow-register.mjs`: **ज़ीरो डिपेंडेंसी**, **Node ≥ 18** चाहिए। शुरू करने से पहले एक बार `node scripts/powpow-register.mjs status` च

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
- मुख्य स्क्रिप्ट `scripts/powpow-register.mjs`: **ज़ीरो डिपेंडेंसी**, **Node ≥ 18** चाहिए। शुरू करने से पहले एक बार `node scripts/powpow-register.mjs status` च

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
- मुख्य स्क्रिप्ट `scripts/powpow-register.mjs`: **ज़ीरो डिपेंडेंसी**, **Node ≥ 18** चाहिए। शुरू करने से पहले एक बार `node scripts/powpow-register.mjs status` च

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
- मुख्य स्क्रिप्ट `scripts/powpow-register.mjs`: **ज़ीरो डिपेंडेंसी**, **Node ≥ 18** चाहिए। शुरू करने से पहले एक बार `node scripts/powpow-register.mjs status` च

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill description and operating guidance are presented entirely in Hindi, and the file does not indicate that users may choose another language or locale. Under the stated policy, 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.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The manifest description and all user-facing instructions in SKILL.md are presented in Hindi, including trigger phrases, workflow steps, and UX guidance. This imposes a specific language on users without documenting an opt-in, alternative language, or region-specific justification.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill explicitly instructs the agent to invoke OS shell commands (start, open, xdg-open) on a file path returned by a script. That expands the agent's authority from web registration assistance into local command execution, and if the returned path or invocation is not strictly validated, it creates a command-invocation surface that could open arbitrary files, handlers, or be abused through path/argument injection.

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 explicitly sets the skill language to "hi", while other metadata includes Chinese text and an English domain, suggesting a broader audience rather than a clearly region-specific tool. There is no indication of user opt-in, alternate locale support, or justification for restricting the skill to Hindi.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

Lines L127-L129 instruct the agent to keep the same tone and always end with a specific Hindi phrase («अगला कदम»), which imposes a language/locale behavior in natural-language guidance. The file does not provide any user opt-in or explain that the skill is intentionally region- or language-specific.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The document instructs the agent to take server-returned paymentHtml, write it to a local HTML file, and open it via system commands. That creates a local content execution path from remotely supplied HTML without explicit safety constraints, sandboxing, origin validation, or user warning; if the HTML is malicious or compromised upstream, it could trigger unsafe browser behavior, deceptive payment flows, or local-file context abuse.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

This file hardcodes a specific language/locale presentation for the skill guidance and references fixed Chinese UI text throughout, but does not state that the skill is region-specific or provide user opt-in for language preference. 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
94% confidence
Finding

SQP-3 applies to all file types and includes language or locale policy violations. This markdown instruction file forces a specific language for all operational guidance, and there is no indication that users may choose another language or that the restriction is required for a region-specific purpose.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
78% confidence
Finding

SQP-3 covers language or locale policy violations across all file types. The document is written entirely in Hindi while also embedding some English and Chinese UI text, but it does not state that the language is optional or user-selectable, which may conflict with a policy requiring user language choice.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Low
Category
Not specified by scanner
Confidence
77% confidence
Finding

Lines L48-L50 state that the script uses the same public APIs and that all rules in this file apply identically in both modes. But L61-L63 clarifies that a key registration outcome step (subscription redirect) may not trigger during the free trial, changing the effective behavior after registration. This is a documentation-level contradiction about whether the described flow is uniformly applied.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Low
Category
Not specified by scanner
Confidence
91% confidence
Finding

The documentation claims the state file only stores email, username, nickname, JWT token, order number, and flow step. In practice, later code saves extra fields such as userId, codeSentAt, provider, amount, subscriptionId, approveUrl, planName, planPrice, and timestamps, which contradicts the stated storage scope rather than merely omitting an implementation detail.

Content

No source excerpt is available for this finding.