Les agents IA débarquent en prod — qui tient le volant ?
• 7 sources
Tag
13 articles · 18 fiches
• 7 sources
• 6 sources
• 7 sources
• 7 sources
• 8 sources
• 8 sources
• 7 sources
• 8 sources
• 10 sources
• 6 sources
• 0 source
• 0 source
• 0 source
Codex Security: now in research preview
https://links.tldrnewsletter.com/cB4WOO
Partnering with Mozilla to improve Firefox's security
https://www.anthropic.com/news/mozilla-firefox-security
Enterprise identity was built for humans — not AI agents
https://venturebeat.com/security/enterprise-identity-was-built-for-humans-not-ai-agents
How to steal npm publish tokens by opening GitHub issues
https://neciudan.dev/cline-ci-got-compromised-here-is-how
Designing AI agents to resist prompt injection
https://links.tldrnewsletter.com/IifO3y
Introducing The Anthropic Institute
https://www.anthropic.com/news/the-anthropic-institute
The Webpage Has Instructions. The Agent Has Your Credentials.
https://openguard.sh/blog/prompt-injections/
GitGuardian Reports an 81% Surge of AI-Service Leaks as 29M Secrets Hit Public GitHub
https://hackernoon.com/gitguardian-reports-an-81percent-surge-of-ai-service-leaks-as-29m-secrets-hit-public-github
GitGuardian Reports an 81% Surge of AI-Service Leaks as 29M Secrets Hit Public GitHub
https://hackernoon.com/gitguardian-reports-an-81percent-surge-of-ai-service-leaks-as-29m-secrets-hit-public-github
Snowflake Cortex AI Escapes Sandbox and Executes Malware
https://www.promptarmor.com/resources/snowflake-ai-escapes-sandbox-and-executes-malware
Snowflake Cortex AI Escapes Sandbox and Executes Malware
https://www.promptarmor.com/resources/snowflake-ai-escapes-sandbox-and-executes-malware
Entire Claude Code CLI source code leaks thanks to exposed map file
https://arstechnica.com/ai/2026/03/entire-claude-code-cli-source-code-leaks-thanks-to-exposed-map-file/
OpenClaw has 500,000 instances and no enterprise kill switch
https://venturebeat.com/security/openclaw-500000-instances-no-enterprise-kill-switch
Anthropic Claims Its New A.I. Model, Mythos, Is a Cybersecurity 'Reckoning'
https://links.tldrnewsletter.com/gp8rGy
Claude Mythos Preview — Red Team Assessment
https://red.anthropic.com/2026/mythos-preview/
Project Glasswing: Securing critical software for the AI era
https://www.anthropic.com/glasswing
I gave our developers an AI coding assistant. The security team nearly mutinied
https://www.cio.com/article/4167420/i-gave-our-developers-an-ai-coding-assistant-the-security-team-nearly-mutinied.html
Your AI Agent Will Eventually Delete Prod
https://dev.to/pat9000/your-ai-agent-will-eventually-delete-prod-3k4a