ClawHub
Back to skill

Security audit

customer-success-manager

Security checks for vulnerabilities and agentic risk

Overview

This is a plain Markdown customer-success guidance skill with expected customer account analysis behavior and no executable code or hidden persistence.

Install only where the agent is allowed to work with customer success records. Configure surrounding tools and permissions so it can access only authorized customer accounts and redact or avoid unnecessary payment, support, and contract details when they are not needed.

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
  • 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 (1)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill explicitly instructs querying broad customer context and reviewing health, usage, feedback, support, and payment-related data without requiring user awareness, consent, scope limitation, or least-privilege checks. In a customer success context, this can expose sensitive business and potentially personal data to an agent workflow that may over-collect or surface information beyond what the invoking user intended.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.