Archived

This repository has been archived on 2026-08-04. You can view files and clone it, but cannot push or open issues or pull requests.

Adam Moussa f90f759e12 Tune checkov severity, wire npm audit, add CI backstop + R720 runbook

checkov: high-signal exposure/access checks -> high, best-practice noise -> low
(was 51 undifferentiated mediums). npm audit wired for Node dep CVEs. Report
collapses the low/info tail to a count. Adds ci/security-review.yml (PR backstop)
and DEPLOY-R720.md (Phase 3 host runbook).

2026-06-15 15:57:34 -04:00

3.5 KiB

Raw Blame History

Phase 3 — Path B deployment (R720 host + CI backstop)

Status: design + scripts; NOT deployed. Needs the R720 (hostname SH-NVR, deprecated NVR, no GPU) and Adam's hands-on involvement. Nothing here has been run against the box. See memory project-security-review-agent.

What Phase 3 delivers

The orchestrator hosted on the R720 as an always-on service (the Path B execution engine).
A headless agentic runner (run_headless.py) so the detector fan-out + proof-or-kill verifier can run unattended (interactive /sh-security-review can't run in CI/cron).
CI backstop (ci/security-review.yml) running the same review.sh on every PR.
Nightly full-repo sweep + planted canary vulns + two-model disagreement on criticals.
Budget/telemetry ceiling against the Max-20x $200/mo Agent SDK credit pool (see memory reference-claude-subscription-billing).

The load-bearing piece to BUILD first: `run_headless.py`

The interactive skill orchestrates subagents via the Claude Code Agent tool (Max-covered). Headless, that must become explicit API/SDK calls. run_headless.py should:

take --scope + target dir, read the in-scope files;
run the 6 detectors (injection/authz/secrets-crypto/iac-iam/web-client/logic) as parallel calls, each fresh context, using the SAME prompts as ~/.claude/commands/sh-security-review.md;
run the proof-or-kill verifier pass;
emit the finding schema JSON that review.sh --agent-findings consumes.
Billing: authenticate via the Claude Agent SDK with the subscription to spend the $200/mo pool before API overflow (NOT a raw key) — see the billing memory. Non-Claude cross-family tiebreak stays on Bedrock/API. ⚠️ This code cannot be validated until it runs with real creds; do not mark done until tested.

R720 host setup (Windows Server 2022, no GPU)

Recommended: run the Python orchestrator in WSL2 or Docker rather than native Windows Python.

git clone https://github.com/amoussa1229/orchestrator onto the box.
Python 3.12 + pip install -r requirements.txt (+ the Agent SDK).
Install the deterministic scanners (semgrep/gitleaks/checkov/cfn-lint/pip-audit) on the box.
Secrets on the box (NOT in git): Agent SDK subscription auth, Bedrock creds, Slack token, repo PATs.
Run as a service (NSSM on Windows, or systemd inside WSL2). Expose to the harness as an MCP/HTTP service (mirror the existing unifi MCP pattern) OR keep it as a local scheduled job.
Scheduler: nightly full-repo sweep → review.sh → Slack report (ALARM-style, see memory feedback_cloudwatch_alarms: only notify on findings, not clean runs).

Anti-complacency reinforcements (Phase 3)

Canary vulns: keep the testbed's planted vulns in a fixture the nightly sweep also scans; if the agent ever misses a known canary, that's a complacency signal → alert.
Two-model disagreement: on confirmed criticals, run the cross-family reviewer (orchestrator GPT-4.1) and flag disagreement for human review.
Budget guard: track output tokens vs the $200/mo pool; stop/alert before overflow.

Open dependencies (Adam)

R720 reachable + WSL2/Docker chosen.
GitHub repo/org secrets: ANTHROPIC_API_KEY (or SDK auth), set vars.SECURITY_REVIEW_AGENTIC=1 once run_headless.py is tested.
Decide: promote ci/security-review.yml into Sea-Haven-Industries/.github as a reusable workflow (per engineering-handbook/cicd.md) vs per-repo copy.
checkov severity filtering (it emitted 51-55 best-practice mediums on payments-dashboard — tune before nightly or the Slack reports are noise).

3.5 KiB Raw Blame History