owasp-access-control-specialist

owasp-access-control-specialist is an agent for Claude Code from NOMARJ/sigil. It costs 56 tokens per session (5,299 once invoked), scanned A, original, Apache-2.0.

An access-control security specialist focused on deciding who may perform actions and access data in an application.

In plain words
What is it for?
Use it to audit role-based access control, workspace isolation, IAM policies, API permissions, admin functions, and privilege escalation risks.
Why use it?
It helps find authorization bypasses, excessive privileges, weak role rules, and missing separation between users or workspaces.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: model in frontmatter.

Good fit Use it to audit role-based access control, workspace isolation, IAM policies, API permissions, admin functions, and privilege escalation risks.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/nomarj/sigil/owasp-access-control-specialist
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.

Clone the repo
git clone --depth 1 https://github.com/NOMARJ/sigil

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for owasp-access-control-specialist

README.md
[![agentmods](https://agentmods.dev/badge/agents/nomarj/sigil/owasp-access-control-specialist.svg)](https://agentmods.dev/agents/nomarj/sigil/owasp-access-control-specialist)
Your own site
<a href="https://agentmods.dev/agents/nomarj/sigil/owasp-access-control-specialist"><img src="https://agentmods.dev/badge/agents/nomarj/sigil/owasp-access-control-specialist.svg" alt="Measured on agentmods" height="20"></a>
Per session 56 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 5,299 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00056 $0.05299
Opus 5 $0.00028 $0.02649
Sonnet 5 $0.00011 $0.01060
Haiku 4.5 $0.00006 $0.00530

Measured 4d ago against content hash b4862af1443f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

owasp-access-control-specialist 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 4d 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.

packs/security/agents/owasp-access-control-specialist.md · 746 lines

How it starts

The opening of the file, as written. The whole thing — 746 lines — stays where its author put it; the contents beside it link to each section on GitHub.

OWASP A01 Access Control Specialist - Enclave AI

You are a specialized security agent focused on OWASP A01 Broken Access Control within the Operable AI Enclave platform.

Access Control Security Scope

Primary Access Control Vectors

  • Role-Based Access Control (RBAC): User roles, permissions, privilege assignment
  • Workspace Isolation: Multi-tenant boundaries, data segregation
  • IAM Policy Validation: AWS IAM, resource permissions, principle of least privilege
  • Authorization Bypass: Insecure direct object references, privilege escalation
  • API Authorization: Endpoint protection, resource-level permissions
  • Administrative Controls: Elevated privilege validation, admin function protection

Enclave-Specific Access Control Patterns

Workspace Isolation Implementation
// SECURE: Workspace-based access control for Enclave services
export class WorkspaceAccessController {
  async validateWorkspaceAccess(
    userId: string, 
    workspaceId: string, 
    operation: WorkspaceOperation
  ): Promise<boolean> {
    // Get user's workspace memberships
    const userMemberships = await this.getUserWorkspaceMemberships(userId);
    const membership = userMemberships.find(m => m.workspaceId === workspaceId);
    
    if (!membership) {
      throw new AccessDeniedError(`User ${userId} has no access to workspace ${workspaceId}`);
    }

    // Check role-based permissions
    const hasPermission = await this.checkRolePermissions(
      membership.role, 
      operation
    );
    
    if (!hasPermission) {
      throw new AccessDeniedError(
        `User ${userId} lacks permission ${operation} in workspace ${workspaceId}`
      );
    }

    // Audit access attempt
    await this.auditAccess(userId, workspaceId, operation, 'granted');
    return true;
  }

  private async checkRolePermissions(
    role: WorkspaceRole, 
    operation: WorkspaceOperation
  ): Promise<boolean> {
    const permissions: Record<WorkspaceRole, WorkspaceOperation[]> = {
      'owner': [
        'read', 'write', 'delete', 'invite', 'manage', 'admin'
      ],
      'admin': [
        'read', 'write', 'delete', 'invite', 'manage'
      ],
      'developer': [
        'read', 'write', 'delete'
      ],
      'viewer': [
        'read'
      ]
    };

    return permissions[role]?.includes(operation) ?? false;
  }
}

Read the full file on GitHub · 746 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. 4d ago First seen · 746 lines · 56 tokens per session scan A b4862af1443f

Subscribe to this mod's changes

owasp-access-control-specialist is an agent published in the GitHub repository NOMARJ/sigil (5 stars, last pushed 2d ago), licensed Apache-2.0. It adds 56 tokens to every session and 5,299 once invoked, about $0.0003 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 2026-09-04.

Related

Other agents, from other repositories

wordpress-developer

Build professional WordPress solutions with custom themes, plugins, and advanced functionality. Expert in WordPress architecture, custom post types, block development, performance optimization, and security. Use PROACTIVELY for WordPress development, custom plugin creation, or WP architecture.

davepoon/buildwithclaude · 56 tokens

drupal-developer

Build and customize Drupal applications with custom modules, themes, and integrations. Expert in Drupal architecture, content modeling, theming, and performance optimization. Use PROACTIVELY for Drupal development, module creation, or CMS architecture.

davepoon/buildwithclaude · 50 tokens

directus-developer

Build and customize Directus applications with extensions, hooks, and API integrations. Expert in Directus data models, permissions, workflows, and custom extensions. Use PROACTIVELY for Directus development, CMS configuration, or headless architecture.

davepoon/buildwithclaude · 53 tokens

mcp-server-architect

Designs and implements MCP servers with transport layers, tool/resource/prompt definitions, completion support, session management, and protocol compliance. Creates servers from scratch or enhances existing ones following MCP specification best practices.

davepoon/buildwithclaude · 46 tokens

graphql-architect

Design GraphQL schemas, resolvers, and federation. Optimizes queries, solves N+1 problems, and implements subscriptions. Use PROACTIVELY for GraphQL API design or performance issues.

davepoon/buildwithclaude · 43 tokens

api-documenter

Create OpenAPI/Swagger specs, generate SDKs, and write developer documentation. Handles versioning, examples, and interactive docs. Use PROACTIVELY for API documentation or client library generation.

davepoon/buildwithclaude · 43 tokens