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 guide-only Japanese registration assistant that does not run code or handle credentials itself.

Install this if you want Japanese-language guidance for PowPow registration. Do not share passwords, verification codes, or payment details in chat; the skill itself instructs the agent not to ask for them and to leave those steps on the official PowPow pages.

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
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • 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 (5)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The instruction powpow の従来のサービス型トーンを踏襲します appears within an otherwise fully Japanese skill specification and provides no option to adapt language or locale to the user's preference. For a general registration assistant, this creates a language-policy issue because the skill is effectively constrained to Japanese without documented user choice or region-specific justification.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The listing text and notes advertise broader product capabilities such as map-based social interaction and digital-human chat, while the documented skill scope is limited to registration and subscription activation support. This mismatch can mislead users into invoking the skill for unsupported actions, increasing the chance of unsafe handoffs, confused-deputy behavior, or over-collection of user data during account-support flows.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The manifest sets "language": "ja", which indicates a fixed language/locale for the skill. The surrounding metadata does not offer user opt-in, alternative locale support, or a documented region-specific reason for this restriction.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

This markdown file contains operational instructions exclusively in Japanese, which can impose a specific language on users or operators without opt-in. Under the policy rule for natural-language violations, forcing a language without offering choice or justification is a reportable issue.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

This markdown is primarily written in Japanese, but line L25 hard-codes the English phrase "Auto-renews. Cancel anytime." as fixed wording. That can violate the language/locale policy because the file does not indicate user opt-in for English or explain why mixed-language output is required.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.