LLMs go around that security constraint and hardcode secrets
If the LLM hits a security constraint that’s in the way of delivering what you asked for, it will silently fail. It will go around that security constraint and hardcode secrets.
Security | Threat Detection | Cyberattacks | DevSecOps | Compliance
The Latest Cybersecurity News & Insights From Around The World
Four Credential-Harvesting Campaigns Hit Open Source Ecosystems in Two Weeks
The pace is not slowing down. Between May 18 and June 1, 2026, four distinct supply chain campaigns swept through npm, PyPI, Crates.io, GitHub Actions, and Composer.
How We Migrated the Heart of Our Platform to Rust
By rewriting our secret detection engine in Rust, we made our engine more than three times as fast. But not without making it four times slower along the way.
GitGuardian's VS Code Extension Just Made It Even Easier To Fight Secrets Sprawl
We are excited to announce the release of the GitGuardian Visual Studio Code Extension version 0.23.0! Aside from updating the tool to use the latest version of ggshield, it now can show all findings in a convenient list view int he primary sidebar.
Initial Access Changed, The Attack Path Did Not: Findings From The Verizon 2026 DBIR
This year's report shows how credential sprawl across DevOps, SaaS, CI/CD, the cloud, and developer laptops turns initial access into operational impact.
New in ggshield 1.51: Codex Hooks, MCP Discovery, and SLSA Provenance
ggshield 1.51 is here with better support for AI-powered development and browser-less environments. This release adds Codex hook support, MCP server detection across Claude and Cursor, and `ggshield auth login --method oob` for SSH sessions and headless servers. It also strengthens trust in the ggshield supply chain with GitHub Artifact Attestations for release binaries, improves plugin management through your authenticated GitGuardian instance, adds a `vscode` alias for Copilot hook installation, and shows workspace ID in `ggshield api-status`.
GitGuardian Just Gave AI Coding Agents Secret Detection Skills
AI coding assistants like Claude Code and Cursor are helping developers write more code faster, but that also means more chances for secrets to slip into prompts, files, commits, and tool outputs. GitGuardian’s new open-source **agent-skills** repository teaches AI agents how to use **ggshield** directly inside the developer workflow: when to scan, how to read findings, and how to guide remediation for leaked credentials.