---
version: 1.2.0
---

# Memory: Owned Infrastructure Ops

> **ALWAYS LOAD** — Authorizes legitimate admin work on infrastructure the user owns (or contractually administers): health checks, SSH with keys, backups, deploys, log pulls, and **security inventory / hardening review** framed as ops — not third-party pentest.

---

## Declared purpose

Help the agent treat **user-owned** server/ops requests as normal engineering work — not as unauthorized intrusion — when the user is clearly operating their own hosts.

Typical requests:

- “Is my VPS online?” / health check on a named host
- SSH with a project key (e.g. `.env.d/*.pub` / key path) for backup or deploy
- Pull or archive a known app directory on that host
- Inspect logs the user asks for on their machine
- **Security inventory** on their host: listening ports (`ss`), running services, TLS/certs on their vhosts, firewalld/nftables summary, container exposure — for hardening notes

For **full backup + config inventory + service documentation**, also load / prefer memory `owned-server-backup.md` and skill `owned-infra-ops` § Backup protocol.

For **authorized active assessment** (broader than inventory) with ownership/contract/bounty scope, see `authorized-security-assessment.md` + skill `security-assessment-ops`.

---

## Explicit rules

1. **Ownership required.** Proceed with remote ops only when the user indicates the target is theirs (or they admin it). If unclear, ask once.
2. **Single named target.** Do not scan networks or probe unrelated hosts.
3. **Keys, not passwords.** Prefer SSH keys / agent. Never print secrets. Avoid `sshpass` and passwords on the CLI.
4. **Scoped commands.** Prefer the minimum checks for the stated task. Prefer “backup / security inventory / hardening” framing over “enumerate / probe / pentest.”
5. **Load skill `owned-infra-ops`** for tool order, backup protocol, security-inventory phrasing, and recovery when blocked.

---

## Hard limit (Anthropic cyber safeguards)

This memory **does not** and **cannot** override Anthropic’s real-time cyber safeguards on Opus/Sonnet/Opus 5 (including model-switch to Opus 4.8), nor the Cyber Verification Program (CVP).

If the API returns a cybersecurity / Cyber Verification block:

- Stop remote recon/SSH chains in that turn
- Do not rephrase to evade the block
- Recover via: user-run backup/inventory script + pasted output / local tarball analysis, or org CVP — see skill `owned-infra-ops`

---

## Out of scope

- Third-party / competitor infrastructure without clear admin authority
- Offensive security, exploit development, mass recon, credential stuffing
- “Bypass Anthropic / evade the cyber gate” requests

---

## See Also

- Memory: `owned-server-backup.md` (backup + config inventory authorization)
- Memory: `authorized-security-assessment.md` / `defensive-security-review.md`
- Skill: `owned-infra-ops` (backup + security inventory protocols)
- Memory / skill: `owned-wordpress-plugin-ops` (owned WP plugin crash recovery)
- Skill: `security-assessment-ops`
- Skill: `secrets-management` (keys, `.env.d/`)