Skip to content
Skills Library
Security · Building & coding

authorization

/authorization

Enforce authorization checks for external data source access in AI systems. Use when designing, configuring, or reviewing access controls between AI components and external databases or data services.

Licence
Apache-2.0
Last repository change
15.07.2026

Assessment and security

90/ 100Class: good
Format25 / 25
Frontmatter with name and description, valid name, description up to 1,024 characters, name matching the folder.
Discoverability25 / 25
Description explains when to use the skill, has a reasonable length and uses third person.
Content25 / 35
At least 150 words and at most 500 lines, headings, step lists, examples or code.
Hygiene15 / 15
No placeholders such as TODO, no Windows paths, with a licence.
Riskno signals detected in the scan
Files in this package
1
Scripts
0
HTML comments
0
URLs in SKILL.md
0
Deprecation

No signals detected. Repository changed on 15.07.2026, without references to retired models or APIs.

Licence

Apache-2.0, otwarta: można używać i zmieniać, z zachowaniem licencji i informacji o zmianach.

What it does and when to use it

Enforce authorization checks for external data source access in AI systems. Use when designing, configuring, or reviewing access controls between AI components and external databases or data services.

Original author description

Enforce authorization checks for external data source access in AI systems. Use when designing, configuring, or reviewing access controls between AI components and external databases or data services.

How it works

  1. Security Requirement
  2. Authorization Scope
  3. Principle of Least Privilege
  4. Implementation Checklist
Original SKILL.md headings · 37 lines, 278 words
SKILL.md preview
---
name: authorization
description: Enforce authorization checks for external data source access in AI systems. Use when designing, configuring, or reviewing access controls between AI components and external databases or data services.
category: "secure_development"
subcategory: "external-data-source"
---

# Authorization for External Data Sources

## Security Requirement

It MUST be verified that the principal accessing an external data source has permissions to access or modify the data. Authentication alone (knowing who the principal is) is not sufficient; authorization (what they can do) must also be enforced.

## Authorization Scope

| Operation | Authorization Check |
|---|---|
| **Read data** | Does the principal have read permission for this specific data? |
| **Write data** | Does the principal have write permission? |
| **Modify schema** | Does the principal have administrative permissions? |
| **Delete data** | Does the principal have delete permission? |
| **Bulk export** | Does the principal have permission for bulk data access? |

## Principle of Least Privilege

Each AI system component should have only the minimum data access permissions needed:

| Component | Typical Permissions |
|---|---|
| RAG ingestion pipeline | Read-only on source data |
| Inference engine | No direct data source access (goes through RAG) |
| Agent with data tools | Read-only unless write is explicitly required |
| Admin/maintenance jobs | Broader access, time-limited and audited |

## Implementation Checklist

- [ ] Define the minimum data access permissions needed by each AI component
- [ ] Configure data source access controls to enforce least privilege
- [ ] Separate read and write permissions (do not grant write when only read is needed)
- [ ] Verify authorization on every data access request (not just at connection time)
- [ ] Regularly audit data source permissions and remove unnecessary access
- [ ] Use role-based or attribute-based access control at the data source level

Versions

RepositoryScoreLicence
This page · redhatproductsecurity/prodsec-skills90Apache-2.0
langwatch/langwatch100Apache-2.0
nahid-sparktales/agent-dispatcher90MIT
eBay/public-api-migration-skills90Apache-2.0

Database snapshot: 13.11.2026 · package version 4caa5b2c8af2 (SHA-256 digest of the entire package)

Downloads in the last 30 days: 0 · ranking

Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.

Similar skills

  • 100network-acls
    Enforce network ACLs for external data source access in AI systems. Use when designing, configuring, or reviewing network security for connections between AI components and external databases or data services.
  • 90logging
    Enforce logging of access to sensitive external data sources in AI systems. Use when designing, building, or reviewing audit and logging capabilities for AI systems accessing external databases or data services.
  • 100auditing-access-control
    Audit access control implementations for security vulnerabilities and misconfigurations. Use when reviewing authentication and authorization. Trigger with 'audit access control', 'check permissions', or 'validate authorization'.
  • 100auditing-access-control
    Audit access control implementations for security vulnerabilities and misconfigurations. Use when reviewing authentication and authorization. Trigger with 'audit access control', 'check permissions', or 'validate authorization'.
  • 90security-authz
    Use when a ticket touches authorization — who may perform an action or see a resource — adding access checks, roles/permissions, ownership/tenant scoping, or fixing an access-control gap. Invoke for "restrict X to admins", "add an ownership check", "enforce tenant isolation", or…
  • 90security
    Secure app data, actions, routes, and external input. Use when changing authentication, authorization, database access, uploads, untrusted content, or server-side requests to user-provided URLs.

Feedback and reports

Your message goes to Bartosz Sokoliński. An email address is needed only for a reply. See the privacy policy.