Back to skill

Security audit

COPPA Guard - 美国儿童隐私合规护栏

Security checks for vulnerabilities and agentic risk

Overview

This skill is a local COPPA text-checking helper with no network, persistence, credential access, or hidden high-impact behavior found.

Installers should understand that this is a Chinese-language, keyword-based compliance aid, not legal advice or a full COPPA audit. It appears safe from a platform-security perspective, but users should not rely on it as their only compliance review.

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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (3)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
87% confidence
Finding

The module docstring, CLI description, help text, and all user-facing output are written exclusively in Chinese while the skill is described as a guard for the U.S. market. This creates a natural-language policy concern because the skill effectively fixes its interface to one language without offering the user a language choice or documenting an explicit opt-in.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
89% confidence
Finding

This markdown is largely written in Chinese while embedding some English labels and examples, but it does not state any language-selection option or user opt-in. For users expecting locale flexibility, the skill documentation effectively imposes a specific language presentation without offering a choice.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
80% confidence
Finding

The module docstring is entirely in Chinese and provides operational guidance and policy context only in that language. This can constitute a language/locale policy issue because the file does not offer an alternative language or indicate that the skill is intentionally limited to Chinese-speaking users or maintainers.

Content

No source excerpt is available for this finding.