From the blog

What we've learned

Security, cost, and architecture insights from building AI infrastructure.

SECURITYMarch 27, 2026·11 min read

43% of MCP configs run bare shell. That's not a misconfiguration, it's the default.

43% of MCP server configs on GitHub use bare shell execution instead of scoped packages. What that means for prompt injection, sandbox escapes, and your filesystem.

Read article →
INCIDENTMarch 25, 2026·14 min read

One compromised scanner, three hacked projects, 100 million downloads poisoned.

LiteLLM supply chain attack traced from Trivy to KICS to PyPI. 100 million monthly downloads compromised. Full attack chain analysis with timeline.

Read article →
INCIDENTMarch 23, 2026·12 min read

I left my AI agent running overnight. Here's what I found in the morning.

$47,000 from an agent loop. 43,175 restarts overnight. 2.5 years of data wiped. Real incidents from OpenClaw, Claude Code, Cursor, Replit, and VS Code Copilot.

Read article →
RESEARCHMarch 21, 2026·11 min read

We compared security in OpenClaw, Claude Code, and Cursor. None of them passed.

OpenClaw has 92 security advisories. Cursor ships 94 unpatched Chromium CVEs. Claude Code's sandbox got bypassed by its own reasoning. We compared all three across 10 dimensions using independent data.

Read article →
ARCHITECTUREMarch 18, 2026·7 min read

Why your AI agent can't detect its own compromise (and what can)

A comparison of SDK-based and proxy-based AI agent governance. Some limitations aren't engineering problems. They're architectural constraints.

Read article →
INCIDENTMarch 17, 2026·10 min read

An AI agent compromised 7 open-source repos in one week. The only defense that worked was another AI.

Between February 20 and 28, hackerbot-claw systematically hit Microsoft, DataDog, Trivy, and four others. A reconstruction of how it worked and what it exploited.

Read article →
SECURITYMarch 15, 2026·8 min read

We scanned 900 MCP configs on GitHub. 75% had security problems.

We scanned 900+ MCP configurations on GitHub. 75% failed basic security checks.

Read article →