~ / rigs / ankush1982 / ai-secure-by-design

ankush1982/ai-secure-by-design

Platform-neutral security and privacy checks for AI-assisted development: a deterministic CLI, MCP server, git hooks and CI action, plus editable scaffolds mapped to NIST SSDF, ISO 27001:2022, DPDP Act 2023 and the AI Security Wiki.

↗ GitHub ★ 2 Apache-2.0 updated 13d ago project Claude CodeCodexCursorGemini CLICopilot Claude plugin
share on X
ARCHETYPE
Pragmatist
A balanced, no-drama setup: some rules, some tools, nothing extreme.
CONTEXT TAX · EVERY TURN
~2.8k tokens
Moderate · median rig: 2.3k · breakdown
GUARDRAILS
0/5
No committed guardrails · details
Quality 0/100 Guardrails v2

Copy this rig

# review before running: this installs third-party code
$ npx degit ankush1982/ai-secure-by-design/.claude ./rig-ai-secure-by-design  # inspect, then merge into .claude/

MCP servers are added to Claude Code at local scope; env vars are shown as YOUR_… placeholders — we never store values. Files are fetched with degit into a separate folder so you can review before merging.

$ npx degit ankush1982/ai-secure-by-design/skills/dpdp-compliance .claude/skills/dpdp-compliance
$ npx degit ankush1982/ai-secure-by-design/skills/healthcare-ai .claude/skills/healthcare-ai
$ npx degit ankush1982/ai-secure-by-design/skills/privacy-by-design .claude/skills/privacy-by-design
$ npx degit ankush1982/ai-secure-by-design/skills/sbd-project-rules .claude/skills/sbd-project-rules
$ npx degit ankush1982/ai-secure-by-design/skills/secure-by-design .claude/skills/secure-by-design
$ curl -fsSL --create-dirs -o .claude/agents/profiler.md https://raw.githubusercontent.com/ankush1982/ai-secure-by-design/main/agents/profiler.md
$ curl -fsSL --create-dirs -o .claude/agents/regime-reviewer.md https://raw.githubusercontent.com/ankush1982/ai-secure-by-design/main/agents/regime-reviewer.md
$ curl -fsSL --create-dirs -o .claude/agents/scaffold-generator.md https://raw.githubusercontent.com/ankush1982/ai-secure-by-design/main/agents/scaffold-generator.md

This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 16.2k rigs:

{
  "permissions": {
    "deny": [
      "Read(./.env)",
      "Read(./.env.*)",
      "Read(**/.env)",
      "Read(~/.ssh/**)",
      "Bash(git push --force:*)",
      "Read(**/*.pem)",
      "Read(.env)",
      "Read(~/.aws/**)",
      "Read(**/*.key)",
      "Read(**/.env.*)",
      "Bash(git push --force*)",
      "Bash(rm -rf:*)",
      "Bash(rm -rf *)",
      "Bash(sudo *)",
      "Bash(sudo:*)",
      "Bash(rm -rf /)",
      "Bash(git push -f:*)",
      "Read(.env.*)",
      "Bash(git reset --hard*)",
      "Bash(rm -rf /*)"
    ],
    "ask": [
      "Bash(git push:*)",
      "Bash(git push *)",
      "Bash(gh pr merge *)",
      "Bash(git commit:*)",
      "Bash(rm *)",
      "Bash(gh pr merge:*)",
      "Bash(gh pr create *)",
      "Bash(git reset --hard:*)",
      "Bash(npm publish:*)",
      "Bash(git rebase *)"
    ]
  }
}

Skills (5)

Subagents (3)

profilerScans a project on first install. Detects language, frameworks, ORM, AI SDKs, auth library, cloud markers, and schema fields that look like personal data. Returns a structured JSON profile. Read-only
regime-reviewerReviews a code diff (PR or staged changes) against the regimes declared in privacy-security-manifest.yaml. Returns a verdict — APPROVE / REQUEST-CHANGES / BLOCK — with itemised findings per regime. Re
scaffold-generatorGenerates a single product-code scaffold by reading the matching template, substituting manifest-driven values, and writing the file to the user's repo. Idempotent. Invoke from /sbd-deploy or /sbd-add

Slash commands (5)

/sbd-add/sbd-check/sbd-deploy/sbd-evidence/sbd-init

Cursor rules (1)

secure-by-design · always

Similar rigs

copied ✓