safe-agent-engineering-suite
Integrated agent workspace guardrails and verifiable software-delivery pipeline for autonomous coding workflows.
| Size | Folder | Inside |
|---|---|---|
| 15.3 kB | p1-workspace-guard/ | 4 source files |
| 9.7 kB | p5-delivery-packager/ | 3 source files |
| 3.3 kB | examples/ | 1 example |
| 1.5 kB | tests/ | 1 test file |
| 7 kB | (root) | 3 config files · 3 docs |
| Size | Path |
|---|---|
| 30 B | .gitignore |
| 1.7 kB | LICENSE.md |
| 1.5 kB | PREVIEW.md |
| 1.4 kB | README.md |
| 385 B | commercial-manifest.json |
| 3.3 kB | examples/safe-agent-pipeline.mjs |
| 5.1 kB | p1-workspace-guard/src/command-policy.mjs |
| 6.8 kB | p1-workspace-guard/src/filesystem-shield.mjs |
| 1.1 kB | p1-workspace-guard/src/index.d.ts |
| 2.3 kB | p1-workspace-guard/src/index.mjs |
| 1.7 kB | p5-delivery-packager/src/index.d.ts |
| 230 B | p5-delivery-packager/src/index.mjs |
| 7.8 kB | p5-delivery-packager/src/packager.mjs |
| 316 B | package.json |
| 1.7 kB | release-manifest.json |
| 1.5 kB | tests/integrated.test.mjs |
Already bought this?
View your purchasesREADME
Safe Agent Engineering Suite (Bundle A)
Complete in-process filesystem guardrails, command execution policy, deterministic packaging, and cryptographic review receipts for autonomous AI agents.
What Is This Bundle?
The Safe Agent Engineering Suite unites two critical infrastructure products extracted from MIMARIO into a unified agent safety workflow:
- Agent Workspace Guard SDK (
P1): In-process runtime guardrails restricting AI agents to authorized workspace boundaries with 120 adversarial red-team tests (blocking path traversal, multi-dot evasion, symlink breakouts, dangerous commands, and shell chaining). - Verifiable Delivery Packager (
P5): Deterministic packaging with canonical JSON manifests, executable bit auditing (mode & 0o111 === 0), and cryptographically signed delivery receipts.
Pricing
- Standalone P1: $149
- Standalone P5: $79
- Bundle Founding Price: $199 (Instant $29 saving)
Quickstart
# 1. Run integrated test
node --test tests/integrated.test.mjs
# 2. Run end-to-end demo
node examples/safe-agent-pipeline.mjs
Security scan report
Scanned by X402 Git, OSV (opens in a new tab) and Socket (opens in a new tab) — passed on all three. Findings from Socket are listed below.
- secrets
- none found
- X402 Git
- size limits
- within caps
- X402 Git
- known malware
- no dependency manifests to check
- OSV
- known vulnerabilities
- no dependency manifests to check
- OSV
- dependency behaviour
- nothing on a direct dependency · 1 in transitive packages
- Socket
- instruction smuggling
- none found
- X402 Git
- what it can do
- nothing to declare
- X402 Git
What this can do
links to 1 host in its docs · nothing runs at install
Findings (1)
- LOWSocket SBOM Resolver — Socket SBOM Resolver (transitive) — no lockfile, so installs are not reproducible
Releases 1
- v1.0.02026-09-16
release: v1.0.0 commercial source edition