Keep the computer your AI agents run on patched every morning: one bot watches for new security advisories, another checks what's installed, applies only verified small updates and holds anything bigger for your OK: AI agent prompt
New CVEs and actively exploited bugs keep coming, and the machine your agents run on needs patching to keep up. Ken Reiners (@Ken_LinkWell), a former NASA security engineer and Navy veteran, shared his setup on X (Oct 23, 2026). A watcher bot follows X for new CVEs and zero-days, a builder bot checks the agents' computer read-only first, and a 9 a.m. routine applies only checksum-verified patch-level updates. Bigger changes (repo PRs, major versions, secrets) wait for his approval. That morning, advisories covered LiteLLM, Node, Next.js, Pillow, Go, certifi, PHP and WordPress. The builder updated Node, Go, Pillow, certifi and Python packages, found nothing compromised, and skipped software that wasn't installed.
SecurityPatch managementintermediateThe prompt
Every morning at [TIME], act as the patch manager for the computer my AI agents run on. 1) Collect the last 24 hours of security advisories (new CVEs, zero-days, actively exploited bugs) from [SOURCES, e.g. official vendor advisories, the CISA Known Exploited Vulnerabilities list, trusted security accounts on X]. 2) Read-only first: list what's actually installed on this machine (OS packages, language runtimes like Node, Python and Go, pip/npm packages, containers) and match each advisory to installed software. Ignore advisories for software that isn't installed and say so. 3) Apply on your own ONLY patch-level updates from official sources, and verify each one against its official checksum or signature before installing. 4) Do NOT apply major-version upgrades, changes to code repositories, anything touching secrets or keys, or anything that needs a restart of [CRITICAL SERVICES]. List those for my approval with the risk of waiting. 5) After updating, check that [KEY SERVICES/AGENTS] still run. Report: advisories reviewed, what applied to me, what you patched (old to new version, checksum verified), what's waiting for my yes, and any sign of compromise you noticed.
How to use it
- Copy the prompt above.
- Replace every [bracket] with your own details (or fill in the blanks on AgentPlaybook Real Estate, which remembers your answers for the next prompt).
- Paste it into Grok Bot, Claude Code, CISA KEV and review the answer before you use it.
Works with: Grok Bot, Claude Code, CISA KEV, X
Real-world example: x.com/Ken_LinkWell/status/2113636118914531693
Before you use it: what to check
Already built into this prompt
- List those for my approval with the risk of waiting.
Check yourself
- Check names, dates, numbers and any claim against your own source material before you use the answer. AI can misread or invent details.
Using an AI agent? Download this prompt as a SKILL.md agent skill with these checks built in, or get the .zip for Claude.ai. How to install skills.
Want to make this prompt even better? Grade it with the free prompt grader or build your own with the AI prompt generator.
32 copy-paste agent prompts (PDF) plus 5 new prompts every week.
Get it free