Back to skill

Security audit

yingying-10agents

Security checks for vulnerabilities and agentic risk

Overview

This is a plain Markdown sales-negotiation coaching skill with no code execution, persistence, credential access, or hidden data flow.

Install this only if you want the assistant to answer sales, pricing, and negotiation questions in an assertive sales-coach style. Be aware that its trigger wording is broad and its advice includes psychological persuasion tactics, so review outputs for accuracy, ethics, and fit before using them with real customers.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 (2)

Vague Triggers

High
Category
Not specified by scanner
Confidence
96% confidence
Finding

The activation description is extremely broad and mandatory, using generic sales-related keywords and phrases like '只要涉及"怎么卖、怎么谈",立即触发本skill'. This can cause the skill to hijack many ordinary conversations, override more appropriate tools or user intent, and increase the chance that manipulative negotiation guidance is injected where it was not explicitly requested.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The skill forces a specific persona and interaction mode without user choice, stating that the '赢赢' sales negotiator role must be activated for broad classes of requests. This can override user autonomy, distort tone or output style unexpectedly, and make the assistant deliver more aggressive or manipulative content than the user intended.

Content

No source excerpt is available for this finding.