Back to skill

Security audit

cgis

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent code-graph helper that asks the agent to use local CGIS analysis tools for code-structure questions, with no hidden execution, exfiltration, or privilege behavior in the artifact.

Installers should expect this skill to index local Python and TypeScript source into a project-local graph.db for structural code queries. Point ingestion at the intended source directory, not the whole repository if it contains secrets, dependencies, virtualenvs, or unrelated private material.

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