Security audit
Agent CLI Builder
Security checks for vulnerabilities and agentic risk
Overview
This skill is a coherent guide for building agent-facing TypeScript CLIs and includes appropriate safety boundaries for installs, credentials, network calls, and writes.
Install this skill only if you want an agent to help build production-style CLIs. Before allowing generated commands to run, review any package installs, login or registration flows, global writes, Skill synchronization, live API calls, or data-changing operations, and keep real credentials out of chat and command arguments.
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
Static analysis
No suspicious patterns detected.