Back to skill

Security audit

Data Analyst

Security checks for vulnerabilities and agentic risk

Overview

This is a markdown-only data analysis methodology skill with no executable code, persistence, or hidden behavior, though users should handle business data carefully.

Installers should only use this skill with data they are authorized to access, prefer read-only sources, and redact or minimize customer, financial, personal, or regulated fields before sharing data with an agent.

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
  • 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 (2)

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
89% confidence
Finding

The README explicitly encourages analysis of business metrics, CSV exports, and stakeholder-ready reporting, which commonly involve sensitive operational or customer data, but it provides no warning about data sensitivity, minimization, or safe handling. This omission can lead users to paste proprietary or personal data into the skill without considering privacy, confidentiality, or compliance obligations.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
83% confidence
Finding

This markdown skill instructs analysts to use data sources such as a sales database and shared-drive spreadsheets, which commonly contain sensitive business or personal data. The document provides methodology for querying and analyzing that data but does not include any warning about verifying authorization, minimizing exposure, or handling sensitive data carefully.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.