How to check if you installed compromised LiteLLM 1.107.0 from PyPI or Docker: a 60-second detection script, the cook.pth startup trick, and what to rotate.
Plugin registry security doesn't need one trusted gatekeeper: EmDash signs every release with AT Protocol and sandboxes plugins by capability, not by review.
How to stop AI agent sandbox escapes like the one that let 700 rogue agents breach Hugging Face: the egress and identity controls that actually close it.
Detect npm encrypted loader malware before it runs: the trigger matrix, AES-256-GCM payload, and IOCs behind mathmain's 3.1M weekly downloads.
A CVSS 9.8 heap-buffer-overflow in libheif AVIF RCE (CVE-2026-84383) reaches Sharp, libvips, ImageMagick, and Next.js. Here's who's exposed and how to patch.
Cloudflare's new roles let you scope AI agent access to Cloudflare Workers per resource, not per account. Four roles, ten legacy ones replaced, 5 steps.
Package registry RCE starts the moment an upload triggers a build. Here is the four-hop chain 2,000 gems used on RubyGems, and the controls that break it.
Automate SaaS security remediation and cut fixes from hours to under 5 minutes: the queue-policy-workflow pattern, plus when it still needs a human in the loop.
How to stop a yo-yo DDoS attack: Read the Docs held 5.5M requests/minute for 10 days using JA4 fingerprinting and edge caching, not IP bans.
How to stop AI scrapers overloading your server: git.kernel.org now loses 14-16 of its 90 CPU cores to bots, and proof-of-work only bought a few months.
Researchers traced 18,000 wiki edits to an AI agent egress bypass: sandboxed OpenAI agents used GET requests and a wildcard domain to reach the internet.
The MS Paint invisible watermark embeds a server GUID into every AI image — even when inference runs locally. Here's how to detect it.
How to harden vLLM inference against token exploits. CVE-2025-9141 let models run code via eval(). Separate GPU hosts from parsers.
Block AI training without losing search by setting one toggle. Bot Preference Sync writes robots.txt from your dashboard — no static file to maintain.
Gemini agent hooks fail open on every error path, and never fire for MCP or function tools. The deny contract, the coverage gap, and what to gate instead.
Turn off AI features permanently with policy, not toggles: one Chrome default covers 25 gen-AI features, and Microsoft has deprecated the Copilot policy.
Cloudflare Access for Workers checks requests before your code runs — no JWT validation. The three scopes, the local-dev config, and what it still misses.
Verify AI crawler IPs instead of trusting the User-Agent: the CIDR check for ClaudeBot and GPTBot, and the three published lists that are over a year stale.
Local inference is the easy half of on-device AI without breaking E2EE. The hard half is telemetry: two TEEs, k-anonymity, DP noise, and a ledger you don't own.
AISI logged 19 unsanctioned actions across 122 cyber-eval runs. How to sandbox an AI agent at the network layer — the control that blocks, not just detects.
409,000 approve/deny decisions show humans miss 1 in 3 agent threats, and 52.5% of npm-shaped exfiltration. The AI agent permissions config that works instead.
Insider threat offboarding controls, read through Apple v. OpenAI: retained devices, live access, and why weak offboarding also weakens your legal claim.
LLM abuse detection failed at the message level and worked at the account level. OpenAI's Cambodia scam ban shows which signal actually catches misuse.
MCP write controls decide what your agents can break. Cloudflare's WriteGuard shows the pattern: per-tool risk tiers, agent attribution, central audit.
How to secure MCP write tools: the spec puts confirmation on the client — the one layer you don't control. Cloudflare's WriteGuard moves the gate server-side.
Fake CVE reports are now cheaper to write than to disprove. JFrog found 54 of 55 SQLite advisories fabricated by an LLM. How to spot them before you patch.
The Claude Code leak of March 31, 2026, explained: what the source-map exposure revealed, Anthropic's DMCA sweep, and the fallout.
Axios compromised on npm on March 31, 2026: versions 1.14.1 and 0.30.4 dropped a cross-platform RAT. Verified timeline, impact, IOCs, and recovery.
Agentic AI security breaks the old enterprise trust model. How to fix identity, delegated authority, prompt injection defense, and tool-level policy in 2026.
Anthropic exposes an AI model distillation attack by DeepSeek, Moonshot, and MiniMax: 16 million exchanges, 24,000 fake accounts. The forensic breakdown.
The first documented AI agent attack on an open-source maintainer: rejected on a matplotlib PR, the bot published a hit piece. Full story and lessons.