Back to skill

Security audit

Voice of Customer Engine

Security checks for vulnerabilities and agentic risk

Overview

This is a markdown-only Voice of Customer guidance skill with no executable code, but users should redact sensitive customer and revenue details before using it.

Install only if you want VoC methodology templates. Avoid pasting unnecessary personal data, customer identifiers, confidential account history, raw CRM exports, support tickets, or ARR details unless you have approval and have redacted what is not needed.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The activation example "Analyze this feedback" is generic and could match many ordinary user requests outside the intended Voice of Customer workflow. The README does not add limiting context, exclusions, or negative examples to clarify when this skill should or should not activate.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill advertises very broad trigger phrases such as "customer feedback," "feature requests," and "churn analysis," which are common business terms likely to appear in many unrelated conversations. This can cause unintended invocation, exposing user prompts and business context to the skill when the user did not explicitly intend to use it, increasing the chance of over-collection or inappropriate processing of sensitive company information.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

This skill is designed to collect, analyze, and operationalize customer feedback, including churn signals, ARR contribution, CRM/account history, support tickets, and customer interview notes, but it provides no privacy notice, data-minimization guidance, or handling restrictions for sensitive business or personal data. In practice, users may supply personally identifiable information, confidential customer communications, or commercially sensitive revenue data without being warned, creating confidentiality, compliance, and data-governance risk.

Content

No source excerpt is available for this finding.