Ssn
Description
A System Security Number for every AI agent — its own Unix identity (private $HOME, workspace, scrubbed env, no net by default), plus a journal of everything it did. The box is disposable; the identity is permanent.
Installation
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open the source below and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
README
ssn
**A System Security Number for every AI agent.**
Your AI agent runs commands on your machine with *your* user, *your* home directory, *your* environment variables full of API keys. `ssn` gives it what it actually deserves: its own identity — a private `$HOME`, a workspace, a scrubbed environment, no network by default, and a journal of everything it did. The box is disposable. **The identity is permanent.**
你不需要"相信"这个 Agent。你只需要把它当成一个普通、但不太靠谱的用户。 给它上户口:自己的家、自己的账号、自己的流水账。
$ ssn create researcher --owner $USER
issued SSN for "researcher" (owner jason)
home: /home/jason/.ssn/agents/researcher/home
$ ssn run researcher --workdir ~/code/myrepo -- claude -p "fix the tests"
$ ssn log researcher --since 1h
2026-09-01T21:14:03+08:00 run.start agent=researcher argv=["claude","-p","fix the tests"] workdir=...
2026-09-01T21:19:47+08:00 run.end agent=researcher argv=["claude","-p","fix the tests"] exit=0 duration_ms=344213
The three-line acceptance test
If these three lines don't behave as shown, `ssn` is broken. They run in CI on every push ([`internal/runner/integration_linux_test.go`](internal/runner/integration_linux_test.go)):
ssn create researcher
ssn run researcher --workdir . -- sh -c 'echo HOME=$HOME; ls /home; \
(exec 3<>/dev/tcp/1.1.1.1/443) 2>/dev/null && echo NET_OK || echo NET_FAIL'
Expected: `HOME=/home/agent`, `/home` contains only `agent` (your real home is not hidden — it is **not mounted**), and `NET_FAIL`.
How it works
v0 is a thin, auditable wrapper around [bubblewrap](https://github.com/containers/bubblewrap) (Linux user namespaces — the same machinery Flatpak uses):
┌─ what the agent sees ──────────────────────┐
│ /home/agent ← its own home (rw) │
│ /workspace ← your repo, bind-mounted │
│ /usr /etc ... ← the OS, read-only │
│ $HOME=/home/agent, env scrubbed, no keys │
│ no network (unless --allow-net) │
│ its own pid/ipc/uts namespaces │
└──────────
Related Skills
Fastapi Review
Review a FastAPI application for architecture, async correctness, dependency injection, Pydantic schemas, secu
Security Defense in Depth
Implement multi-layered testing and security best practices.
Security SecLists Official Repository
[OWASP Testing Guide](https://owasp.org/www-project-web-security-testing-guide/)
Security Threat Hunting with Sigma Rules
Use Sigma detection rules to hunt for threats and analyze security events
Security Maintenance Walkthrough - 2026-03-29
- Re-triaged the full 2026-03-15 security finding set against current `main` and wrote a fresh current-head re
Security Google Workspace Model Armor
Filter user-generated content for safety
Security Related Agents
Django Reviewer
Expert Django code reviewer specializing in ORM correctness, DRF patterns, migration safety, security misconfi
Token Auditor
Scans ui/src/ for hardcoded visual values, duplicate components, and shadcn replacement candidates; produces d
Gitnexus Security Boundary Reviewer
GitNexus security and trust-boundary reviewer. Use for auth, permissions, secrets, injection, unsafe parsing,