Back to skill

Security audit

Agent Nil — Act 0

Security checks for vulnerabilities and agentic risk

Overview

This skill is a small, disclosed game integration that sends optional game messages and moves to a public MCP endpoint, with no local execution or privileged access in the artifact.

Install only if you are comfortable sending game moves, optional operator names, and freeform messages to the listed external MCP service; do not transmit private or sensitive data because the artifact says received signals are recorded verbatim.

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