Version updated for https://github.com/luckyPipewrench/pipelock to version v2.3.0. This action is used across all versions by 0 repositories. Action Type This is a Composite action. Go to the GitHub Marketplace to find the latest changes. Action Summary Pipelock is an open-source AI security tool designed to act as a firewall for AI agents, providing network scanning, process containment, and policy enforcement. It solves the problem of securing sensitive environments by generating independently verifiable, mediator-signed action receipts outside the agent’s trust boundary, ensuring accountability and preventing unauthorized actions. Its key capabilities include agent-external attestation, proof of agent activities, and compatibility with various AI development tools and frameworks.

Version updated for https://github.com/luckyPipewrench/pipelock to version v2.2.0. This action is used across all versions by 0 repositories. Action Type This is a Composite action. Go to the GitHub Marketplace to find the latest changes. Action Summary Pipelock is an open-source AI agent firewall that enhances security by monitoring and controlling agent behavior. It prevents data exfiltration, injection, and unauthorized access by scanning outbound and inbound requests, sandboxing agent processes, and enforcing security policies. Additionally, it provides signed, independently verifiable action receipts to ensure transparency and accountability.

Version updated for https://github.com/luckyPipewrench/pipelock to version v2.1.2. This action is used across all versions by 0 repositories. Action Type This is a Composite action. Go to the GitHub Marketplace to find the latest changes. Action Summary Pipelock is an open-source “agent firewall” designed to secure AI agents by monitoring and controlling their interactions with the internet. It prevents data exfiltration, injection attacks, and unauthorized access by scanning inbound and outbound traffic, sandboxing agent processes, and enforcing tool usage policies. Additionally, it provides signed evidence of agent activity, ensuring robust runtime security for environments handling sensitive information.

Version updated for https://github.com/luckyPipewrench/pipelock to version v2.1.1. This action is used across all versions by 0 repositories. Action Type This is a Composite action. Go to the GitHub Marketplace to find the latest changes. Action Summary Pipelock is an open-source agent firewall and local runtime designed to secure AI agents by providing network scanning, process containment, and enforcement of tool usage policies in a single binary. It prevents sensitive data leaks, such as API keys, and mitigates malicious activity by intercepting and analyzing HTTP traffic, blocking unauthorized requests without requiring code changes to the agent. Pipelock supports various AI frameworks and offers flexible deployment options, including standalone binaries, Docker containers, and proxy modes.