Back to skill

Security audit

ken-gain

Security checks for vulnerabilities and agentic risk

Overview

This skill is a narrow display-only helper that reports measured Ken benchmark results or an empty state without asking to install code, persist state, or access unrelated data.

Install only if you want a display-only Ken benchmark scoreboard. It should not edit files or use credentials; if an agent invoking it starts running the benchmark harness or reading .env files, that is outside this skill's stated behavior and should require separate user approval.

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