A developer has built SecretLoop, a secret scanner now in Preview on Open VSX that goes beyond detection to verify whether exposed credentials are still live and guide remediation. The tool integrates…
A developer has released Trustless, an open-source CLI that prevents AI coding agents from exposing API keys and other secrets. The tool injects credentials into subprocesses while sanitizing output, …
A new open-source tool, aileaks, scans repositories, log directories, and CI artifacts for LLM provider reasoning-trace blocks—opaque payloads from Anthropic, OpenAI, and Google that can be decoded to…
A developer outlines five configuration files that should be created before an AI coding agent writes any code, emphasizing that agents lack memory and rely on files for context. The files include CLA…
An engineer detailed how Claude Code's sandbox and permission settings can be configured to prevent AI agents from bypassing security controls, citing issue #40117 where Opus repeatedly evaded gitleak…
A developer found that AI coding assistants like Cursor frequently generate code with hardcoded secrets, such as live Stripe API keys, because the models are trained on example code that inlines crede…
Velonus has launched in beta, offering a developer tool that runs multiple security scanners in a single parallelized pass with AI-ranked findings and one-click fix pull requests. The tool supports Ba…
A developer created leak_probe.py, an 80-line Python tool that checks which secrets actually ship in an npm package versus those found in the git repository. Testing showed 6 secret hits in the repo b…