Back to skill

Security audit

PowPow رجسٹریشن — بابل رجسٹر کریں، سفرنامہ نقشے پر پن کریں، ڈیجیٹل انسان سے چیٹ کریں

Security checks for vulnerabilities and agentic risk

Overview

The skill is purpose-aligned for PowPow account setup, but it handles passwords, verification codes, login tokens, and payment identifiers with under-disclosed local state exposure.

Install only if you are comfortable letting the agent create a PowPow account, send registration requests, receive your email verification code, generate or use your password via an environment variable, and create optional Alipay or PayPal subscription orders. Run cleanup after use, avoid sharing payment credentials with the agent, and be aware that status output and temp files may reveal account and payment workflow details beyond the login token.

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 (23)

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
- مرکزی اسکرپٹ `scripts/powpow-register.mjs`: **زیرو ڈپینڈنسی**، **Node ≥ 18** درکار۔ شروع کرنے سے پہلے ایک بار `node scripts/powpow-register.mjs status` چلا کر

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
- مرکزی اسکرپٹ `scripts/powpow-register.mjs`: **زیرو ڈپینڈنسی**، **Node ≥ 18** درکار۔ شروع کرنے سے پہلے ایک بار `node scripts/powpow-register.mjs status` چلا کر

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
- مرکزی اسکرپٹ `scripts/powpow-register.mjs`: **زیرو ڈپینڈنسی**، **Node ≥ 18** درکار۔ شروع کرنے سے پہلے ایک بار `node scripts/powpow-register.mjs status` چلا کر

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
- مرکزی اسکرپٹ `scripts/powpow-register.mjs`: **زیرو ڈپینڈنسی**، **Node ≥ 18** درکار۔ شروع کرنے سے پہلے ایک بار `node scripts/powpow-register.mjs status` چلا کر

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
- مرکزی اسکرپٹ `scripts/powpow-register.mjs`: **زیرو ڈپینڈنسی**، **Node ≥ 18** درکار۔ شروع کرنے سے پہلے ایک بار `node scripts/powpow-register.mjs status` چلا کر

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
- مرکزی اسکرپٹ `scripts/powpow-register.mjs`: **زیرو ڈپینڈنسی**، **Node ≥ 18** درکار۔ شروع کرنے سے پہلے ایک بار `node scripts/powpow-register.mjs status` چلا کر

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
- مرکزی اسکرپٹ `scripts/powpow-register.mjs`: **زیرو ڈپینڈنسی**، **Node ≥ 18** درکار۔ شروع کرنے سے پہلے ایک بار `node scripts/powpow-register.mjs status` چلا کر

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
- مرکزی اسکرپٹ `scripts/powpow-register.mjs`: **زیرو ڈپینڈنسی**، **Node ≥ 18** درکار۔ شروع کرنے سے پہلے ایک بار `node scripts/powpow-register.mjs status` چلا کر

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
- مرکزی اسکرپٹ `scripts/powpow-register.mjs`: **زیرو ڈپینڈنسی**، **Node ≥ 18** درکار۔ شروع کرنے سے پہلے ایک بار `node scripts/powpow-register.mjs status` چلا کر

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
- مرکزی اسکرپٹ `scripts/powpow-register.mjs`: **زیرو ڈپینڈنسی**، **Node ≥ 18** درکار۔ شروع کرنے سے پہلے ایک بار `node scripts/powpow-register.mjs status` چلا کر

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
- مرکزی اسکرپٹ `scripts/powpow-register.mjs`: **زیرو ڈپینڈنسی**، **Node ≥ 18** درکار۔ شروع کرنے سے پہلے ایک بار `node scripts/powpow-register.mjs status` چلا کر

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
81% confidence
Finding

The skill description is written entirely in Urdu and presents the assistant's behavior and onboarding flow in that language, with no indication that users may choose another language. Per the policy rule, forcing a specific language without opt-in is a natural-language policy concern unless the locale restriction is clearly documented and justified.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill explicitly collects and processes highly sensitive data including passwords, email addresses, and one-time verification codes, and it instructs the agent to act on the user's behalf for account creation and login. Without an explicit user-facing privacy notice, consent boundary, retention policy, and disclosure of how credentials/session artifacts are handled, users may unknowingly expose secrets to the agent or platform, increasing the risk of account takeover or unintended credential storage.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
80% confidence
Finding

The file is written as a fixed Urdu-language interaction pattern and explicitly instructs the agent to maintain a specific conversational style for this service. There is no indication that the user may choose another language or that the language restriction is required for a documented regional/compliance reason, which creates 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
93% confidence
Finding

The manifest sets "language": "ur", which indicates a fixed language/locale choice. The file does not offer an opt-in, alternative language selection, or a region-specific justification for restricting the skill to Urdu, which fits the language/locale policy violation criteria.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

This markdown file uses a fixed non-user-selectable language for the operational instructions, and later references Chinese-only error text as part of the workflow. The policy requires flagging language or locale constraints when the skill forces a specific language without user opt-in or clear justification.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The document is entirely written in Urdu and appears to prescribe that language for the interaction flow without indicating any user choice, fallback, or localization handling. In a payment and account-activation context, forcing a language can cause user misunderstanding of billing terms, subscription behavior, and recovery steps, which raises safety and trust concerns even if it is not a classic code-execution issue.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The file is written primarily in Urdu and includes Chinese interface strings, but it does not state that this language choice is optional or limited to a region-specific audience. Under the stated policy, forcing a specific language/locale 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
77% confidence
Finding

The file presents all user-facing operational guidance in a fixed language context and references Chinese interface labels, but it does not indicate that language selection is optional or user-driven. Under the stated policy, forcing a specific language or locale without opt-in can be a natural-language policy concern.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The guidance tells the agent to send screenshots 'as needed' and when the user 'should be convinced by seeing it,' but it does not define clear permission boundaries, user-consent requirements, or exclusions. In an agent context, vague trigger conditions can cause over-sharing of media, off-topic responses, or unnecessary use of local/hosted assets without a precise user request.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The status command claims to show no credentials, but it only removes token before printing the saved state. Other sensitive values such as approveUrl, subscriptionId, outTradeNo, email, and account workflow metadata remain exposed, which can leak session or payment-related information to logs, terminals, or calling agents that trust the comment.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Low
Category
Not specified by scanner
Confidence
89% confidence
Finding

The file header states that only limited fields are persisted, but the implementation stores additional sensitive workflow data including userId, provider details, amounts, subscription IDs, approval URLs, and timestamps. This mismatch can cause operators or downstream tooling to handle the state file less carefully than warranted, increasing the chance of unintended disclosure from the temp directory.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
92% confidence
Finding

The generated HTML hard-codes lang="en" and uses English-only page text such as Redirect to PayPal. This is a natural-language locale choice imposed by the skill without offering the user a language option or documenting a justified locale constraint.

Content

No source excerpt is available for this finding.