Before You Hand an AI Agent the Keys
AI agents now sign in as you. What a dinner-planning agent taught us about agent identity, credentials and access control, and the five questions to ask first.
#ai-security#agentic-ai#identity-security
Thought Leadership
6 articles in this category
The AI Risk We Keep Finding Is the App You Built
Vibe coding security risks are already in production. Four client cases of AI-built apps that went business-critical untested, and the supply chain behind them.
#ai-security#application-security#shadow-ai
The Admins You Didn't Count
"Who's in Domain Admins?" is the wrong question. How nested groups, service accounts, and DCSync rights create Tier-0 access your membership audit never sees.
#active-directory#privileged-access#tier-0
Your Git History Still Has the Password You Deleted
Deleting a password from a repo doesn't remove it. How attackers pull secrets from git history, self-hosted servers, and reused vault keys, and how to stop it.
#secrets-management#devsecops#source-code-security
The Hugging Face Breach and the Case for AI Failover
An autonomous AI agent breached Hugging Face, and its responders couldn't use OpenAI or other frontier models to investigate. Why you need an AI failover plan.
#ai-security#incident-response#ai-resilience
Your AI Governance Policy Won't Stop a Prompt Injection
AI governance frameworks like the NIST AI RMF and ISO 42001 set the rules. They can't prove your AI resists attack. Why fast-moving, nondeterministic AI also needs adversarial testing.
#ai-security#governance#adversarial-testing