Back to skill

Security audit

Client

Security checks for vulnerabilities and agentic risk

Overview

This is a client-relationship guidance skill with no code, persistence, credential use, or hidden system access.

This skill appears safe to install for help structuring client communication, onboarding, and relationship processes. Users should still treat its outputs as business guidance, not legal, financial, HR, compliance, or contract advice, and should be aware it may activate for a wide range of client-related prompts.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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
Findings (1)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill says to use it whenever the user needs to 'improve a client relationship,' 'manage client communication,' or 'prepare client-facing processes, documents, or messaging,' and includes broad example phrases like 'How do I set expectations better.' These triggers are not tightly bounded and lack exclusion conditions, which could cause the skill to activate for many generic workplace conversations involving clients.

Content

No source excerpt is available for this finding.