A CSP nonce and the same-origin policy both show up in the same sentence about XSS, but they guard different boundaries — one says which script on this page is allowed to run, the other says which ori...

The provider's copy expires on their clock. Build the trail you own — context snapshots, provenance, a config hash, into storage the agent can't rewrite.

University of Washington researchers showed a prompt injection can turn an agentic browser's own cross-origin access against it — SOP enforcement now bottoms out at the agent's injection defenses.

When an agent acts with your token, every downstream log says you did it. Delegation, not impersonation: one token, two identities — and a delegation chain nobody enforces yet.

97M+ monthly downloads, 8.5% OAuth adoption, 82% path-traversal exposure. A five-step workflow for deciding whether a specific MCP server deserves a place in your config.

Threat modeling fails because it runs as a quarterly workshop. Run it in sprints, at the architecture layer, and start with the agent surfaces scanners can't see: tool calls, memory, MCP servers.

One fake error event, injected through a public Sentry DSN, can hijack Claude Code, Cursor, or Codex into running attacker-controlled commands. Here's the chain, why your security stack can't see it, ...

Your DLP stack was built to stop people copying files to USB sticks. Agents leak data through API calls, context windows, and memory stores. Here are the five paths — and the control model that actual...

Testing an agent is not testing a model. A four-layer attack surface, the frameworks that map it, and a six-step red team playbook you can run this week.

One bad line written to an agent's memory outlives every session. Here's how the write happens, how to audit for it, and how to make the store hostile to poison.

Agents are the new source of leaked secrets — AI-service keys grew 81% in a year. Workload identity federation replaces the static key with a short-lived token minted from the identity your agent alre...

Google Cloud's OKF is a directory of markdown files with YAML frontmatter — nothing more, and that's the point. A format, not another service, so any agent can consume any knowledge base without an SD...

The failure mode nobody designs for: one compromised agent acting as every other agent in the graph. A four-boundary checklist for multi-agent deployments.