Skip to content
Agentmart
Submit a tool

security-review

Dedicated data-flow security pass over a diff or a repo — deeper than the security dimension of /tech-review.

Skill by PlatformRelay

IndexedMIT★ 1
Write a review

Chalk Labs

Need help deploying security-review?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/platformrelay-security-review

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Dedicated data-flow security pass over a diff or a repo — deeper than the security dimension of /tech-review. Traces untrusted input to sinks, checks authn/authz, secrets, crypto, RBAC, TLS, and supply chain. Use before a release, when touching auth/secrets/RBAC/webhooks, or when the operator says "security review this".

Use cases: data, security, finance

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/security-review

What's inside

Skill name
security-review
Description
Dedicated data-flow security pass over a diff or a repo — deeper than the security dimension of /tech-review. Traces untrusted input to sinks, checks authn/authz, secrets, crypto, RBAC, TLS, and supply chain. Use before a release, when touching auth/secrets/RBAC/webhooks, or when the operator says "security review this".
License
MIT
Instructions
38 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

# security-review — data-flow security pass

A focused security review that reasons about the code like a researcher: it **traces data flow** from
untrusted sources to dangerous sinks, rather than pattern-matching keywords. Dispatch the
`tech-reviewer` role in a security-only mode (or, for a Go operator, lean on the repo's own security
gates). Read-only.

## Step 1 — scope
Diff/branch or whole repo? Name the trust boundaries in play (API server, webhook admission, external
sinks/MQ endpoints, secret references, user-supplied CR fields).

## Step 2 — trace (the core of the pass)
For each untrusted input (CR spec fields, webhook payloads, HTTP responses, env), follow it to where
it's used and check the guard at each hop:
- **Injection / unsafe use** — command, path, template, CEL/JSONPath, SQL-ish backends.
- **AuthN/AuthZ** — SAR (`CanI`) pre-checks before privileged reads; RBAC least-privilege, no `*`
  verbs / cluster-admin; tenancy scope enforced.
- **Secrets** — only via `secretRef`; never in `spec`/`status`, logs, or events; short-lived tokens
  preferred.
- **Crypto / transport** — TLS verification on by default; no `InsecureSkipVerify` without an
  explicit, logged opt-in; no weak randomness for security-relevant values.
- **Supply chain** — image signing/SBOM/`govulncheck`/`gosec`/Trivy/pinned deps/gitleaks present and
  green.
- **Resource safety** — no unbounded `List`; deadlines on external calls; no panic path reachable from
  input.

## Step 3 — report
Findings table (ID · Sev P0–P3 · vulnerability class · data-flow `source → sink` · evidence
`path:line` · fix). Verdict: SECURE / FIX-REQUIRED / AT-RISK. Feed P0/P1 to `/write-story` and, for a
diff, note them on the PR. Save the report to `agent-context/inbox/reports/<YYYY-MM-DD>-security-<slug>.md`
and append a **REPORT** line to the INBOX.

## Do not
- Keyword-scan without tracing the flow — a real finding names source→sink.
- Report a theoretical issue you didn't verify against the code.
- Log or paste any secret you find while reviewing.

From PlatformRelay/Kaddy, MIT.

More from PlatformRelay/Kaddy

Signals

Stars
1
Forks
0
Open issues
0
Last commit (this folder)
Jul 20, 2026 (3 months ago)
Last release
Jul 21, 2026 (3 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from PlatformRelay

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get security-review running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying security-review?

CallGet help
Cite this page

security-review skill. Agent Mart. https://agentmart.dev/skills/platformrelay-security-review (last updated 2026-10-24)