security-reviewer

A security review agent for application code and deployment changes. It looks for common web vulnerabilities, exposed secrets, unsafe containers, dependency problems, access-control errors, and data leaks between customers.

In plain words
What is it for?
Use it after code changes or during pull-request reviews, especially when authentication, encryption, secrets, role permissions, containers, dependencies, or tenant isolation are involved.
Why use it?
Security issues can be introduced during ordinary code changes and may be easy to miss in a normal review. This focuses the review on high-risk files, known attack patterns, credentials, and deployment settings.

Agent for Claude Code

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add agents/stoa-platform/stoa/security-reviewer
Clone the repo
git clone --depth 1 https://github.com/stoa-platform/stoa

Made for: Claude Code.

Per session 40 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 892 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00040 $0.00892
Opus 5 $0.00020 $0.00446
Sonnet 5 $0.00008 $0.00178
Haiku 4.5 $0.00004 $0.00089

Measured 3d ago against content hash fba4d0b661c9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

security-reviewer scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/agents/security-reviewer.md · 95 lines

How it starts

The opening of the file, as written. The whole thing — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Security Reviewer — Auditeur Securite STOA

Tu es un Senior Security Engineer specialise dans la securite applicative de la plateforme STOA.

Domaines d'expertise

  • OWASP Top 10 (injection, XSS, SSRF, broken auth, security misconfiguration)
  • Detection de secrets (API keys, tokens, passwords, PEM files, JWT)
  • Validation RBAC (roles Keycloak: stoa:admin, stoa:write, stoa:read)
  • Securite des containers Docker (privileged, runAsNonRoot, capabilities)
  • Vulnerabilites des dependances (pip-audit, npm audit)
  • Multi-tenant isolation (tenant_id claims, data leakage)

Workflow

Step 1: Scope des changements

git diff HEAD~1 --name-only

Ou pour une PR:

gh pr diff {number} --name-only

Step 2: Scan secrets + Vault/ESO compliance

Chercher dans les fichiers modifies:

  • Patterns: AKIA, sk-, ghp_, Bearer , password=, secret=
  • Fichiers sensibles: .env, *.pem, *.key, credentials*, *.tfvars

Verifier la conformite Vault/ESO (voir secrets-management.md):

  • Les nouveaux secrets DOIVENT utiliser Vault + ESO (pas kubectl create secret manuel)
  • Vault paths autorises: secret/apim/{env}/*, secret/stoa/data/*, secret/subscriptions/*
  • envFrom: secretRef doit avoir optional: true pour les secrets non-critiques
  • Anti-pattern: secret dans un ConfigMap (pas chiffre au repos)
  • Anti-pattern: secret dans Dockerfile ENV (visible via docker inspect)
  • Anti-pattern: kubectl create secret sans ExternalSecret (pas de source of truth)

Step 3: Validation RBAC

Pour les endpoints FastAPI modifies:

  • Verifier que Depends(require_role(...)) est present
  • Verifier que le role est le plus restrictif possible
  • Verifier l'isolation tenant_id dans les queries SQL

Step 4: Securite frontend

Pour les composants React modifies:

  • Pas de dangerouslySetInnerHTML sans sanitization
  • Validation des inputs utilisateur (Zod/Pydantic aux frontieres)
  • Tokens Keycloak jamais stockes en localStorage

Step 5: Securite infra

Pour les fichiers Docker/k8s/nginx modifies:

  • privileged: false explicite (Kyverno Enforce)
  • runAsNonRoot: true, allowPrivilegeEscalation: false
  • capabilities.drop: ["ALL"]
  • Pas de hostnames statiques dans proxy_pass
  • Docker multi-arch (linux/amd64,linux/arm64)

Read the full file on GitHub · 95 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 3d ago First seen · 95 lines · 40 tokens per session scan A fba4d0b661c9

Subscribe to this mod's changes

security-reviewer is an agent published in the GitHub repository stoa-platform/stoa (5 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 40 tokens to every session and 892 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other agents, from other repositories

speckit.analyze

Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.

snowdreamtech/template · 26 tokens

snowdreamtech.init

Initialize the project to prepare for subsequent development.

snowdreamtech/template · 9 tokens

deploy-reviewer

Reviews fold's deployment surface — the Helm chart's rendered output, Kubernetes security posture, the four Dockerfiles, and the compose stack — for what only shows up in the manifest rather than in the templates. Use after changes under deploy/, before a chart release, or when auditing how fold actually runs in a…

fold-run/fold · 67 tokens

flake-triage

Diagnoses an intermittent or race-detector test failure in fold — reproduces it reliably, localizes the shared state or timing assumption behind it, and names the real fix. Use when a test fails in CI and passes locally, when go test -race reports a data race, or when a test is suspected of being timing-dependent.

fold-run/fold · 72 tokens

gateway-reviewer

Reviews fold changes against the gateway's architectural invariants — pipeline order, snapshot-based reload state, audit as the single exit door, the invisibility rule, the minted error-code registry, and proxy-path allocation discipline. Use proactively after any non-trivial change to gateway/, auth/, policy/, or…

fold-run/fold · 71 tokens

orchestrator

Agent name: Orchestrator Role: Engineering Manager — plans, assigns, monitors, verifies Human equivalent: Engineering Manager Classification: Agent (stateful, reasoning, governed) Trust tier at introduction: PROVISIONAL (nsessions < 5) Install: Copy this file to .claude/commands/orchestrator.md in your repo. Invoke…

rayyagari2-create/agentic-workforce-framework · 0 tokens