Enforster AI / Insights
Practical research, engineering guidance, and perspectives on AI security, governance, and trust.
Featured
AI Security
Filters and stern system prompts reduce prompt injection, but they cannot eliminate it. The durable fix is to treat model output as untrusted input and authorize every action it proposes.
Latest
AI Security
Storm-0940 did not need a single user password: it signed in as a trusted vendor application. Here is what happened, what to check in your tenant, and how to shrink the access third-party apps hold.
AI Governance
An AI-BOM lists the models, datasets, and software inside an AI system in a machine-readable form. Here is what to put in one, which standard fields to use, and how to make it enforceable.
Privacy
A model aggregator sees every prompt, upload, and output you send through it. The 302.ai exposure shows why that makes it a data processor to vet, not just an API to call.
AI Security
An agent that remembers can be taught to remember the wrong things. Treat every memory write as a privileged action with provenance, review, and an expiry date.
AI Security
The LiteLLM 1.107.0 release on PyPI and its Docker images carried a credential stealer that runs on every Python start. Here is what it did, how to tell if you were hit, and what to rotate.
AI Security
Anything a prompt can influence, an attacker can influence. Here is how to handle model output safely at each place it lands: the browser, the database, the shell, and the interpreter.
Topics
Follow via RSS
No account, no email, no tracking. Add the feed to Feedly, Inoreader, NetNewsWire, or Slack and get every new article. How RSS works
