Security audit
Infographic & Data Viz
Security checks for vulnerabilities and agentic risk
Overview
This skill is a non-executable data-visualization guidance package with disclosed, purpose-aligned handling of real data, chart design, accessibility, and human-approved publishing.
Before installing, understand that the skill may guide an agent to use your brand materials and real analytics or research data to make charts. That access fits the purpose, but you should avoid giving it confidential datasets unless the output is intended for public use and has been reviewed.
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
