Back to skill

Security audit

PowPow 登録 — 登録して旅行記を地図にピン留め、デジタルヒューマンとチャット

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed PowPow account-registration helper that also supports optional subscription checkout, but it handles sensitive account and payment-adjacent data.

Install only if you are comfortable letting the agent help create a PowPow account and submit your email, password, verification code, and optional avatar to the official PowPow service. Payments are optional; if used, complete them yourself in the opened Alipay or PayPal checkout, run the cleanup command afterward, and delete any generated checkout HTML files from the temp directory on shared devices.

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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • 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 (24)

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
- コアスクリプト `scripts/powpow-register.mjs`:**依存関係ゼロ**、**Node ≥ 18** が必要。開始前に一度 `node scripts/powpow-register.mjs status` を実行して環境が使えることを確認します。

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
- コアスクリプト `scripts/powpow-register.mjs`:**依存関係ゼロ**、**Node ≥ 18** が必要。開始前に一度 `node scripts/powpow-register.mjs status` を実行して環境が使えることを確認します。

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
- コアスクリプト `scripts/powpow-register.mjs`:**依存関係ゼロ**、**Node ≥ 18** が必要。開始前に一度 `node scripts/powpow-register.mjs status` を実行して環境が使えることを確認します。

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
- コアスクリプト `scripts/powpow-register.mjs`:**依存関係ゼロ**、**Node ≥ 18** が必要。開始前に一度 `node scripts/powpow-register.mjs status` を実行して環境が使えることを確認します。

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
- コアスクリプト `scripts/powpow-register.mjs`:**依存関係ゼロ**、**Node ≥ 18** が必要。開始前に一度 `node scripts/powpow-register.mjs status` を実行して環境が使えることを確認します。

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
- コアスクリプト `scripts/powpow-register.mjs`:**依存関係ゼロ**、**Node ≥ 18** が必要。開始前に一度 `node scripts/powpow-register.mjs status` を実行して環境が使えることを確認します。

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
- コアスクリプト `scripts/powpow-register.mjs`:**依存関係ゼロ**、**Node ≥ 18** が必要。開始前に一度 `node scripts/powpow-register.mjs status` を実行して環境が使えることを確認します。

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
- コアスクリプト `scripts/powpow-register.mjs`:**依存関係ゼロ**、**Node ≥ 18** が必要。開始前に一度 `node scripts/powpow-register.mjs status` を実行して環境が使えることを確認します。

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
- コアスクリプト `scripts/powpow-register.mjs`:**依存関係ゼロ**、**Node ≥ 18** が必要。開始前に一度 `node scripts/powpow-register.mjs status` を実行して環境が使えることを確認します。

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
- コアスクリプト `scripts/powpow-register.mjs`:**依存関係ゼロ**、**Node ≥ 18** が必要。開始前に一度 `node scripts/powpow-register.mjs status` を実行して環境が使えることを確認します。

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
- コアスクリプト `scripts/powpow-register.mjs`:**依存関係ゼロ**、**Node ≥ 18** が必要。開始前に一度 `node scripts/powpow-register.mjs status` を実行して環境が使えることを確認します。

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The entire skill description is presented only in Japanese, and the workflow appears designed around Japanese-language interaction without any stated option for the user to choose another language or locale. Under the policy, forcing a specific language without user opt-in is a natural-language policy concern unless the locale restriction is explicitly justified.

Content

No source excerpt is available for this finding.

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
94% confidence
Finding

The skill clearly instructs the agent to use environment variables for passwords and to make network requests, create payment orders, and open payment pages, but it declares no explicit tool scope or permissions boundary. In a system that relies on manifest-declared capabilities, this weakens reviewability and consent, and can allow sensitive operations to occur without clear platform enforcement or user visibility.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The top-level description markets convenience but does not clearly warn that the agent will collect or handle highly sensitive data such as email addresses, passwords, verification codes, avatar file paths, and may also create and open payment orders on the user's behalf. That omission undermines informed consent and increases the risk of users oversharing credentials or authorizing financial actions they did not fully understand.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The description and operational instructions are written as if the skill should always interact in Japanese, but there is no statement that the user may choose another language or that Japanese is required for a region-specific compliance reason. 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.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The notes describe a very broad agent-delegated workflow: sending verification codes, performing registration, creating orders, and tracking payments, with only vague fallback behavior and no explicit consent, scope, or exclusion boundaries. In an account-creation and payment-adjacent skill, this ambiguity can lead to over-collection of user data, unintended actions on third-party services, or activation in contexts the user did not clearly authorize.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

This skill file is written entirely in Japanese and provides no indication that users or operators may choose another language. Per the policy, forcing a specific language or locale without opt-in is a natural-language policy violation unless the locale restriction is clearly justified, which is not stated here.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The document explicitly states that the agent can perform registration, send verification codes, and log users in through the same public APIs as the website, but it does not require an explicit user-consent or sensitive-data handling warning. In this skill context, the agent is expected to collect and act on passwords, email verification codes, and session-related state, so missing guardrails materially increases the risk of unsafe credential handling, unauthorized account actions, or phishing-like UX.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The script persists a session token in a temp-directory state file and creates additional payment HTML artifacts in temp directories, but cleanup only deletes the single state file. This leaves residual sensitive artifacts on disk, including one-click login material and payment-flow files, which could be accessed later by other local users, malware, backups, or forensic recovery on a shared or multi-user system.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
95% confidence
Finding

The manifest sets the skill language to "ja" and the listing title/keywords are Japanese, but there is no visible indication that users can opt into another language or that the Japanese-only constraint is required for a documented regional purpose. This creates a natural-language locale policy concern because the skill appears to enforce a specific language by default.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
76% confidence
Finding

This markdown file documents a behavior that repeatedly queries a remote payment/subscription API, which affects privacy and network activity. While the file mentions the destination host, it does not explicitly warn the user that the script will continue transmitting account/order identifiers during polling until payment completion.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
79% confidence
Finding

In the markdown flow, the skill directs the operator to open a payment page and then perform repeated status checks against the platform. Because this behavior can affect privacy and system/network activity, the skill description should explicitly disclose it to the user rather than only implying it through command steps.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
83% confidence
Finding

This line presents a fixed Chinese error string for users who attempt password login on third-party accounts. Because no user language choice or locale constraint is described here, it appears to impose a specific language without opt-in.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
95% confidence
Finding

The file’s natural-language interface, help text, status messages, and error messages are consistently presented in Chinese, including the command documentation and runtime output. Because there is no opt-in, fallback, or documented locale constraint, this creates a language/locale policy concern under the natural-language policy rule.

Content

No source excerpt is available for this finding.