tool-use-execution-security
CommunitySecure tool calls in agentic AI systems.
Software Engineering#input-validation#sandboxing#command-injection#tool-calling#agentic-security#permission-management
Authormaruakshay
Version1.0.0
Installs0
System Documentation
What problem does it solve?
Review agentic AI systems for insecure tool calling, unsafe code or shell execution, excessive permissions, confirmation bypass, argument injection, sandbox escape risk, and action-policy failures across languages and frameworks.
Core Features & Use Cases
- Validation and whitelisting of tool calls (names, arguments, and outputs) before they are executed.
- Sandboxed execution environments and per-request scope to prevent privilege escalation and data exposure.
- Real-world scenarios include agents coordinating with shell tools, code execution, or API calls where safety controls are critical.
Quick Start
Ask the AI to review an existing tool-calling implementation and propose concrete mitigations.
Dependency Matrix
Required Modules
None requiredComponents
Standard package💻 Claude Code Installation
Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.
Please help me install this Skill: Name: tool-use-execution-security Download link: https://github.com/maruakshay/mii-ai-security/archive/main.zip#tool-use-execution-security Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
Agent Skills Search Helper
Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.