openafw
NewOpenAFW is a local agent firewall — keep your secrets off the model, the API relay, and the supply chain. Local credential masking, per-route model routing, and security detectors on the wire.
Summary
OpenAFW is a local agent firewall that protects your secrets by masking credentials before they reach the model, routing requests through per-route model policies, and detecting security threats on the wire.
- It helps developers safely use AI agents and APIs without exposing sensitive data to third parties or supply chain risks.
Install & Usage
mkdir -p .claude/skillsAdd the configuration to .claude/skills/openafw.md
/openafwUse Cases
Usage Examples
/openafw mask --prompt 'Use API key sk-1234 to call the weather service'
/openafw route --model gpt-4 --policy strict --request 'Get user data from /api/users'
/openafw detect --input 'DROP TABLE users; -- malicious SQL injection'
Security Audits
Frequently Asked Questions
What is openafw?
OpenAFW is a local agent firewall that protects your secrets by masking credentials before they reach the model, routing requests through per-route model policies, and detecting security threats on the wire. It helps developers safely use AI agents and APIs without exposing sensitive data to third parties or supply chain risks.
How to install openafw?
To install openafw: create the skills directory (mkdir -p .claude/skills), then add the config to .claude/skills/openafw.md. Finally, /openafw in Claude Code.
What is openafw best for?
openafw is a other categorized under General. It is designed for: security, api, agent. Created by openafw.
What can I use openafw for?
openafw is useful for: Mask API keys and tokens in prompts before sending them to an LLM, preventing accidental leakage.; Route different API calls to specific models or endpoints based on security policies and data sensitivity.; Detect and block malicious payloads or injection attempts in real-time as they traverse the agent pipeline.; Enforce least-privilege access by restricting which models can process requests containing certain credentials.; Audit and log all agent-to-API interactions for compliance and security monitoring without exposing secrets.; Integrate with existing CI/CD pipelines to scan supply chain dependencies for credential exposure risks..