ClawHub
Back to skill

Security audit

PPT代做

Security checks for vulnerabilities and agentic risk

Overview

This is a Markdown-only business guidance skill for PPT service monetization, with no code execution, persistence, credential handling, or hidden behavior found.

This appears safe to install as a guidance skill. Users should treat it as business-operations advice and avoid using PPT outsourcing for academic dishonesty, copyright infringement, false advertising, spam, or platform-policy violations.

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 (2)

Tp2

High
Category
MCP Tool Poisoning
Confidence
85% confidence
Finding

Mixing characters from multiple Unicode scripts in a single identifier is a common technique to create visually ambiguous tool names.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The activation description is broad ('when you plan to engage in or optimize PPT ghostwriting, call this skill'), which can cause the agent to invoke the skill in loosely related contexts without clear boundaries. Over-broad triggering increases the chance of unintended use, policy bypass via irrelevant activation, or inappropriate business-growth guidance being surfaced where it is not contextually safe or desired.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.