Back to skill

Security audit

PowPow စာရင်းသွင်းခြင်း — ပူဖောင်း စာရင်းသွင်းပါ၊ ခရီးသွားမှတ်တမ်းကို မြေပုံပေါ်တင်ပါ၊ ဒစ်ဂျစ်တယ်လူသားနှင့် စကားပြောပါ

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed PowPow account-registration helper with optional payment-order support, and its sensitive actions are mostly user-directed and purpose-aligned.

Install only if you want an agent to create or help activate a PowPow account. Expect to provide an email address, verification code, username, password choice, and optionally an avatar or phone number. For subscription flows, confirm before opening any generated checkout page and complete payment only on the official Alipay or PayPal page. Run the cleanup command when finished so the temporary token state is removed.

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 Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
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
- အဓိက script `scripts/powpow-register.mjs` — **မှီခိုမှု သုည**၊ **Node >= 18** လိုအပ်သည်။ စတင်မလုပ်မီ `node scripts/powpow-register.mjs status` ကို တစ်ကြိမ် လု

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
- အဓိက script `scripts/powpow-register.mjs` — **မှီခိုမှု သုည**၊ **Node >= 18** လိုအပ်သည်။ စတင်မလုပ်မီ `node scripts/powpow-register.mjs status` ကို တစ်ကြိမ် လု

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
- အဓိက script `scripts/powpow-register.mjs` — **မှီခိုမှု သုည**၊ **Node >= 18** လိုအပ်သည်။ စတင်မလုပ်မီ `node scripts/powpow-register.mjs status` ကို တစ်ကြိမ် လု

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
- အဓိက script `scripts/powpow-register.mjs` — **မှီခိုမှု သုည**၊ **Node >= 18** လိုအပ်သည်။ စတင်မလုပ်မီ `node scripts/powpow-register.mjs status` ကို တစ်ကြိမ် လု

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
- အဓိက script `scripts/powpow-register.mjs` — **မှီခိုမှု သုည**၊ **Node >= 18** လိုအပ်သည်။ စတင်မလုပ်မီ `node scripts/powpow-register.mjs status` ကို တစ်ကြိမ် လု

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
- အဓိက script `scripts/powpow-register.mjs` — **မှီခိုမှု သုည**၊ **Node >= 18** လိုအပ်သည်။ စတင်မလုပ်မီ `node scripts/powpow-register.mjs status` ကို တစ်ကြိမ် လု

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
- အဓိက script `scripts/powpow-register.mjs` — **မှီခိုမှု သုည**၊ **Node >= 18** လိုအပ်သည်။ စတင်မလုပ်မီ `node scripts/powpow-register.mjs status` ကို တစ်ကြိမ် လု

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
- အဓိက script `scripts/powpow-register.mjs` — **မှီခိုမှု သုည**၊ **Node >= 18** လိုအပ်သည်။ စတင်မလုပ်မီ `node scripts/powpow-register.mjs status` ကို တစ်ကြိမ် လု

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
- အဓိက script `scripts/powpow-register.mjs` — **မှီခိုမှု သုည**၊ **Node >= 18** လိုအပ်သည်။ စတင်မလုပ်မီ `node scripts/powpow-register.mjs status` ကို တစ်ကြိမ် လု

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
- အဓိက script `scripts/powpow-register.mjs` — **မှီခိုမှု သုည**၊ **Node >= 18** လိုအပ်သည်။ စတင်မလုပ်မီ `node scripts/powpow-register.mjs status` ကို တစ်ကြိမ် လု

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
- အဓိက script `scripts/powpow-register.mjs` — **မှီခိုမှု သုည**၊ **Node >= 18** လိုအပ်သည်။ စတင်မလုပ်မီ `node scripts/powpow-register.mjs status` ကို တစ်ကြိမ် လု

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill description is written entirely in Burmese/Myanmar language, and the file does not indicate that the user can choose another language or that the skill is intentionally limited to a Burmese-speaking audience. This creates a natural-language policy concern because it effectively imposes a specific language without user opt-in.

Content

No source excerpt is available for this finding.

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
94% confidence
Finding

The skill performs sensitive actions involving environment variables, network access, account registration, login-link generation, and payment-related flows, but it declares no explicit tool scope or permission boundary. That creates an authorization gap where a host agent may grant broader capabilities than necessary, increasing the chance of unintended data exposure or external actions without clear operator review.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The skill instructs the agent to automatically open locally generated files and external payment/login pages using system handlers. Auto-launching browser or local file targets without an explicit consent checkpoint can surprise users, trigger unsafe navigation, and make phishing or local-file abuse harder to distinguish from legitimate actions.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The file instructs the agent to continue using PowPow's service-expression style as a fixed conversational mode. This is a natural-language policy concern because the skill does not provide an option for the user to choose a different language or locale style, nor does it justify the constraint as region-specific compliance.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The listing markets capabilities such as travel-map posting and digital-human chat that the skill description explicitly says it does not perform. This creates a scope mismatch that can mislead users and reviewers about what the agent will do, increasing the risk of unsafe invocation, consent confusion, or overbroad trust in automation handling registration and payment flows.

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 sets "language": "my" on L14, while the listing text and notes also suggest a fixed locale presentation. Under the policy, forcing a specific language without user opt-in or a documented region-specific justification 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
95% confidence
Finding

The file instructs the agent to always respond in a fixed style and to end every reply with a specific section, regardless of the user's preferences. This is a prompt-level policy override that can degrade user autonomy and make the agent less responsive to higher-priority conversational context, though it does not directly create code-execution or data-exfiltration risk.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
87% confidence
Finding

The skill text presents a fixed-language success message string ("支付成功") inside otherwise Burmese instructions, and later also includes English UI text, but does not indicate that the skill is region-specific or that users can choose their preferred language. This can violate language/locale policy when a skill effectively forces specific locale output without 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 file presents operational instructions in Burmese, with several Chinese UI strings, but does not state that the skill is region- or language-specific or provide an opt-in language choice. Under the policy, forcing a specific language or locale without user choice is a natural-language policy violation.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
87% confidence
Finding

The instruction says to use screenshots 'as needed' and send a relevant image if the user does not understand or needs to 'see' the product, but it does not clearly define boundaries for when the skill should send images versus continue with text. This broad condition can overlap with many ordinary support exchanges and may lead to unintended screenshot delivery.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
91% confidence
Finding

The generated HTML hard-codes lang="en" and uses an English-only page title while the rest of the skill is Chinese. This imposes a specific language on the user without offering a language choice or documenting a justified locale constraint.

Content

No source excerpt is available for this finding.