fix: repo-wide security hardening from ZAP, Scorecard, and CodeQL audit

.github/dependabot.yml

@@ -62,3 +62,17 @@ updates:
       - Aureliolo
     labels:
       - type:chore
+
+  - package-ecosystem: docker
+    directory: /docker/sandbox
+    schedule:
+      interval: daily
+      time: "06:00"
+      timezone: Etc/UTC
+    commit-message:
+      prefix: "chore"
+    open-pull-requests-limit: 5
+    reviewers:
+      - Aureliolo
+    labels:
+      - type:chore

.github/workflows/dast.yml

@@ -19,7 +19,10 @@ jobs:
     runs-on: ubuntu-latest
     permissions:
       contents: read
-      issues: write  # Required by API scan action to create issues for scan findings
+      # The ZAP action creates/updates a single GitHub issue per repo with scan
+      # findings (not one per run). Removing issues:write would cause the action
+      # to fail. The auto-created issue is updated in-place on subsequent runs.
+      issues: write
     steps:
       - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6
         with:

.github/workflows/pages-preview.yml

@@ -233,7 +233,9 @@ jobs:
           CLOUDFLARE_ACCOUNT_ID: ${{ secrets.CLOUDFLARE_ACCOUNT_ID }}
           PR_NUMBER: ${{ needs.build.outputs.pr_number }}
         run: |
-          npm i --no-save wrangler@3.114.17
+          # Scorecard: npm install cannot be hash-pinned for CI-only tools;
+          # --ignore-scripts mitigates post-install script supply-chain risk.
+          npm i --no-save --ignore-scripts wrangler@3.114.17
           npx wrangler pages deploy _site --project-name=synthorg-pr-preview --branch="pr-${PR_NUMBER}"
 
       - name: Comment preview URL

.pre-commit-config.yaml

@@ -14,7 +14,11 @@ repos:
       - id: trailing-whitespace
       - id: end-of-file-fixer
       - id: check-yaml
-        exclude: ^src/ai_company/templates/builtins/
+        exclude: ^(src/ai_company/templates/builtins/|mkdocs\.yml$)
+      - id: check-yaml
+        name: check-yaml (mkdocs, unsafe for !!python tags)
+        args: [--unsafe]
+        files: ^mkdocs\.yml$
       - id: check-toml
       - id: check-json
       - id: check-merge-conflict

CLAUDE.md

@@ -60,6 +60,7 @@ npm --prefix web run test                  # Vitest unit tests
 - **Design spec**: `docs/design/` (7 pages: index, agents, organization, communication, engine, memory, operations)
 - **Architecture**: `docs/architecture/` (overview, tech-stack, decision log)
 - **Roadmap**: `docs/roadmap/` (status, open questions, future vision)
+- **Security**: `docs/security.md` (comprehensive security architecture, hardening, CI/CD security, compliance)
 - **Reference**: `docs/reference/` (research, standards)
 - **REST API reference**: `docs/rest-api.md` — links to standalone Scalar UI page at `docs/_generated/api-reference.html` (both generated by `scripts/export_openapi.py` in CI)
 - **Library reference**: `docs/api/` — auto-generated from docstrings via mkdocstrings + Griffe (AST-based, no imports)

README.md

@@ -121,6 +121,7 @@ graph TB
 | [Architecture](docs/architecture/index.md) | System overview, tech stack, decision log |
 | [API Reference](docs/rest-api.md) | REST API reference (Scalar/OpenAPI) |
 | [Library Reference](docs/api/index.md) | Auto-generated from docstrings |
+| [Security](docs/security.md) | Security architecture, hardening, CI/CD security |
 | [Developer Setup](docs/getting_started.md) | Clone, test, lint, contribute |
 | [User Guide](docs/user_guide.md) | Install, configure, run via Docker |
 

docker/sandbox/Dockerfile

@@ -1,6 +1,6 @@
-FROM node:22-slim AS node-base
+FROM node:22-slim@sha256:9c2c405e3ff9b9afb2873232d24bb06367d649aa3e6259cbe314da59578e81e9 AS node-base
 
-FROM python:3.14-slim
+FROM python:3.14.3-slim@sha256:6a27522252aef8432841f224d9baaa6e9fce07b07584154fa0b9a96603af7456
 
 COPY --from=node-base /usr/local/bin/node /usr/local/bin/node
 COPY --from=node-base /usr/local/lib/node_modules /usr/local/lib/node_modules

docs/api/api.md

@@ -1,3 +1,8 @@
+---
+search:
+  exclude: true
+---
+
 # API Layer
 
 Litestar REST + WebSocket API — controllers, authentication, guards, and channels.

docs/api/budget.md

@@ -1,3 +1,8 @@
+---
+search:
+  exclude: true
+---
+
 # Budget
 
 Cost tracking, budget enforcement, auto-downgrade, quota management, and CFO optimization.

docs/api/communication.md

@@ -1,3 +1,8 @@
+---
+search:
+  exclude: true
+---
+
 # Communication
 
 Inter-agent messaging — bus, dispatcher, delegation, loop prevention, conflict resolution, and meeting protocols.

docs/api/config.md

@@ -1,3 +1,8 @@
+---
+search:
+  exclude: true
+---
+
 # Config
 
 YAML company configuration loading and validation.

docs/api/core.md

@@ -1,3 +1,8 @@
+---
+search:
+  exclude: true
+---
+
 # Core
 
 Shared domain models, base types, and enums used across the framework.

docs/api/engine.md

@@ -1,3 +1,8 @@
+---
+search:
+  exclude: true
+---
+
 # Engine
 
 Agent orchestration, execution loops, task decomposition, routing, and parallel execution.

docs/api/hr.md

@@ -1,3 +1,8 @@
+---
+search:
+  exclude: true
+---
+
 # HR
 
 Agent lifecycle management — hiring, firing, onboarding, offboarding, performance tracking, and promotion/demotion.

docs/api/index.md

@@ -1,3 +1,8 @@
+---
+search:
+  exclude: true
+---
+
 # Library Reference
 
 Auto-generated reference documentation from source code docstrings.

docs/api/memory.md

@@ -1,3 +1,8 @@
+---
+search:
+  exclude: true
+---
+
 # Memory
 
 Persistent agent memory — protocol, retrieval pipeline, shared org memory, consolidation, and archival.

docs/api/observability.md

@@ -1,3 +1,8 @@
+---
+search:
+  exclude: true
+---
+
 # Observability
 
 Structured logging, event constants, correlation tracking, and log sinks.

docs/api/persistence.md

@@ -1,3 +1,8 @@
+---
+search:
+  exclude: true
+---
+
 # Persistence
 
 Pluggable operational data persistence — protocol, configuration, and SQLite backend.

docs/api/providers.md

@@ -1,3 +1,8 @@
+---
+search:
+  exclude: true
+---
+
 # Providers
 
 LLM provider abstraction — protocol, base class, drivers, capabilities, routing, and resilience.

docs/api/security.md

@@ -1,3 +1,8 @@
+---
+search:
+  exclude: true
+---
+
 # Security
 
 Security subsystem — rule engine, trust strategies, autonomy levels, output scanning, and timeout policies.

docs/api/templates.md

@@ -1,3 +1,8 @@
+---
+search:
+  exclude: true
+---
+
 # Templates
 
 Pre-built company templates, personality presets, and template builder.

docs/api/tools.md

@@ -1,3 +1,8 @@
+---
+search:
+  exclude: true
+---
+
 # Tools
 
 Tool system — base class, registry, invoker, built-in tools, and MCP bridge.