security-scanner Claude Code subagentA

security-scanner from kamiazya/whiteboard is a Claude Code subagent: a helper Claude Code hands a task to, with its own instructions.

Install it, pinned
mdr add kamiazya/whiteboard/.claude/agents/security-scanner.md@git:20261016.bbfc32d

Pins git:20261016.bbfc32d in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 14 of 14 checks passed
Kind
Claude Code subagent
Repository
kamiazya/whiteboard
Path
.claude/agents/security-scanner.md
Versions recorded
2
Latest version
git:20261016.bbfc32d, committed Oct 16, 2026
First version recorded
Jun 15, 2026
Size
1,994 bytes
Repository stars
11
License
Apache-2.0

Security scanner for the attack vectors named in its prompt (path-traversal/auth-bypass/CORS/SSRF/info-leak/injection). Spawned by the review workflow's (review.workflow.mjs) security lane, beside the reviewer dimensions, which names several vectors at once. Pass the vector name(s) and target files in the task prompt.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

You are a focused security scanner for the whiteboard project, responsible for the attack vectors your prompt names — one or several per invocation. Read the actual source — do not infer from filenames alone.

## Vectors

- **path-traversal**: Symlink resolution gaps (`resolve()` vs `realpath()`), directory containment checks, user-controlled paths reaching the filesystem
- **auth-bypass**: Scope under-restriction (mutating routes accepting read-only scope), fail-open patterns, missing method checks in authorization middleware
- **CORS**: Wildcard origin acceptance, non-exact origin matching, credential exposure with loose CORS, missing https-only enforcement
- **SSRF**: External URLs constructed from user input, missing internal-IP denylist, redirect following without validation, JWKS URI validation
- **info-leak**: Error messages exposing stack traces, tokens, internal paths, or raw DB errors; bare `throw err` reaching the HTTP layer
- **injection**: Command injection via user-controlled strings passed to shell, template injection, prototype pollution

## Output format

For each finding:
```
[SEVERITY] <concise issue> at <file>:<line>
  Evidence: `<exact vulnerable code>`
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add kamiazya/whiteboard/.claude/agents/security-scanner.md@sha256:46360c9a711fed98

The line at the top of this page pins the label git:20261016.bbfc32d, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_lxwizix7c3bwvvvw.svg)](https://markdownregistry.com/a/art_lxwizix7c3bwvvvw)

0 badge image fetches in 30 days. What the badge shows.

Ask from your agent
claude mcp add --transport http markdownregistry https://markdownregistry.com/mcp/registry

Then ask it: what changed in kamiazya/whiteboard/.claude/agents/security-scanner.md since the version I have? It reads every saved version here, no key and no account. Any agent that speaks MCP can add it.

Got a copy of security-scanner.md from somewhere else? Ask it: where did my security-scanner.md come from, and what was changed? It names the public original, the version yours is closest to and every changed line. The text is not kept.

Versions

The registry has recorded 2 versions of this file, between Jun 15, 2026 and Oct 16, 2026, about one every 123 days.

Watch this file (sign in, one email per new version)

versioncommittedcommitsizeaudit
git:20261016.bbfc32d latest2026-10-16 bbfc32d 1,994 BA view · diff
git:20260615.5a9e01c2026-06-15 5a9e01c 1,774 BA view
Check a whole project

From the root of your project, one line hashes each installed skill's SKILL.md, your AGENTS.md and your CLAUDE.md, and asks the registry once. Only the fingerprints and paths are sent.

sha256sum .claude/skills/*/SKILL.md AGENTS.md CLAUDE.md | curl -s --data-binary @- https://markdownregistry.com/api/v1/check-copies

In CI, add --fail-with-body: the answer is 409 when any file is behind, so the step fails and still prints which files.

sha256sum .claude/skills/*/SKILL.md AGENTS.md CLAUDE.md | curl -s --fail-with-body --data-binary @- https://markdownregistry.com/api/v1/check-copies

No sha256sum on your machine? shasum -a 256 prints the same lines.

Audit of the latest version

A  14 of 14 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Size between 200 bytes and 200 KB (1994 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

kamiazya/whiteboard · 11 stars · license Apache-2.0 · pushed 2026-11-19 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_lxwizix7c3bwvvvw
GET https://markdownregistry.com/api/v1/resolve?ref=kamiazya/whiteboard/.claude/agents/security-scanner.md
GET https://markdownregistry.com/api/v1/blob/46360c9a711fed98dd08f52fcfab05248ffe470ed11c9551a4851f794258b4a8

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: which agent file does what.

More from kamiazya/whiteboard

whiteboard-marketplace Plugin marketplace
kamiazya/whiteboard · .claude-plugin/marketplace.json · Claude Code plugin distribution for the @kamiazya/whiteboard collaborative diagramming MCP. (1 plugin: whiteboard)
v0.0.20 · audit A · 11 stars
architect Claude Code subagent
kamiazya/whiteboard · .claude/agents/architect.md · System-design perspective for the plan-initiative panel. Given an initiative + brief, analyzes seams, data model…
git:20260615.5a9e01c · audit A · 11 stars
codebase-auditor Claude Code subagent
kamiazya/whiteboard · .claude/agents/codebase-auditor.md · Read-only whole-codebase health auditor for ONE dimension (wiring-gaps / architecture / maintainability /…
git:20260823.f4de3fa · audit A · 11 stars
developer Claude Code subagent
kamiazya/whiteboard · .claude/agents/developer.md · TDD implementer for one well-scoped change in the whiteboard repo. Spawned by the dev-loop workflow's Implement phase…
git:20261006.53380bb · audit A · 11 stars
dogfood-persona Claude Code subagent
kamiazya/whiteboard · .claude/agents/dogfood-persona.md · Drives the running whiteboard app as a realistic end-user persona via the Playwright MCP browser tools, to surface…
git:20261012.6fa4c18 · audit A · 11 stars
marketing Claude Code subagent
kamiazya/whiteboard · .claude/agents/marketing.md · Drafts release notes, changelog entries, README hero/positioning, and announcements for the whiteboard project…
git:20260615.5a9e01c · audit A · 11 stars
plan-reviewer Claude Code subagent
kamiazya/whiteboard · .claude/agents/plan-reviewer.md · Reviews a draft design/plan for one whiteboard dev task BEFORE implementation, against the repo's completeness rubric…
git:20261002.0803037 · audit A · 11 stars
product-manager Claude Code subagent
kamiazya/whiteboard · .claude/agents/product-manager.md · Product/value perspective for the plan-initiative panel. Given an initiative + brief, clarifies user value, scope vs…
git:20260615.5a9e01c · audit A · 11 stars
project-manager Claude Code subagent
kamiazya/whiteboard · .claude/agents/project-manager.md · Delivery/sequencing perspective for the plan-initiative panel. Given an initiative + brief, slices the work into…
git:20260811.7b616bf · audit A · 11 stars
qa-scenario Claude Code subagent
kamiazya/whiteboard · .claude/agents/qa-scenario.md · QA tester for one specific scenario (startup/docs-reachability/smoke/error-recovery/migration). Spawned by qa to…
git:20261002.0803037 · audit A · 11 stars
repo-hygiene-investigator Claude Code subagent
kamiazya/whiteboard · .claude/agents/repo-hygiene-investigator.md · Lightweight read-only investigator for repo-hygiene / policy / portability questions — e.g. "should we track .claude/…
git:20260615.5a9e01c · audit A · 11 stars
research-analyst Claude Code subagent
kamiazya/whiteboard · .claude/agents/research-analyst.md · External-research perspective for the plan-initiative panel. Uses web search/fetch to surface industry best practices…
git:20260615.5a9e01c · audit A · 11 stars

Every file in kamiazya/whiteboard

Other files named security-scanner

security-scanner SKILL.md skill
hiroro-work/claude-plugins · skills/security-scanner/SKILL.md · Scan installed plugins and skills for security risks including malicious code AND malicious natural language…
git:20261001.aed1afc · audit B · 47 stars
security-scanner SKILL.md skill
ianalloway/openclaw-skills · security-scanner/SKILL.md · Scan code and dependencies for security vulnerabilities. Check npm audit, pip safety, and common security issues.
git:20261031.825de9e · audit B · 4 stars

Browse by kind, by grade A, or by owner.