ClawHub
Back to skill

Security audit

ping-pong-coach

Security checks for vulnerabilities and agentic risk

Overview

This is a simple Chinese-language table-tennis coaching helper that uses local reference text and a small local calculator script, with no evidence of hidden access, persistence, or data exfiltration.

Install this skill if you want Chinese-language table-tennis training-plan help. Be aware that it may trigger broadly on table-tennis lesson-plan requests and its script only computes stage/progress; the agent relies on the included curriculum reference to form the complete plan.

A.I.G

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

SkillSpector

Vulnerability Patterns
  • 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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (5)

Tp4

High
Category
MCP Tool Poisoning
Confidence
96% confidence
Finding

The declared description promises a teaching-plan generator that outputs a complete staged方案 with technical points, stage durations, current stage determination, and remaining learning time using gender, age, and learning years. The supplied code only calculates the learner's current stage from years studied using hardcoded stage durations and names, then formats a short progress report. While stage judgment and remaining time estimation are present, the primary promised capability—generation of a full instructional/training plan—is absent. Gender is not accepted or used at all, and age is merely echoed in output rather than affecting recommendations. Therefore the actual behavior is substantially narrower than the declared purpose.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The manifest says the skill triggers not only on specific phrases, but also whenever the user '询问乒乓球教学内容、训练计划、阶段安排时'. That scope is ambiguous and broad enough to match ordinary discussion about table-tennis instruction, without clear boundaries or exclusion examples.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The usage section states that mentioning table-tennis teaching plans, study plans, training plans '等' activates the skill. The 'etc.' wording leaves trigger scope open-ended and does not specify what similar phrases count or what should be excluded, increasing unintended invocation risk.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
76% confidence
Finding

This markdown file is entirely written in Chinese and does not indicate that the user can choose another language or that the content is intentionally limited to a Chinese-speaking audience. Under the stated policy, forcing a specific language without user opt-in can be a natural-language policy violation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
93% confidence
Finding

This code file contains all natural-language documentation, usage text, errors, and output strings in Chinese only. Under the stated policy, forcing a specific language without user opt-in is a natural-language policy violation unless the locale restriction is explicitly justified, which is not present here.

Content

No source excerpt is available for this finding.