Agent skill · Audited from source
auth-sec
skill · yaklang/hack-skillsMIT licenceAudited 30 Oct 2026 · source a6bc8e8fefb6
Is it safe? Yes — SAFE, grade B (89/100). We read this skill's source at commit a6bc8e8fefb6 and found no filesystem, network or shell access and no hard-coded secrets. What it does: Entry P1 category router for authentication and authorization. Use when testing login flows, sessions, object authorization, JWT, OAuth, CORS, CSRF, and enterprise SSO weaknesses before any deeper auth topic skill.
Cite
Cite this page
ModelsAtlas. “auth-sec (yaklang/hack-skills)”. Retrieved 30 Oct 2026. https://modelsatlas.com/skills/yaklang/auth-sec
Trust audit
Audit 0.4.1 · source read 30 Oct 2026
SAFE means nothing in the source contradicts what the skill says it does. Grade B is shared by 16,667 of 17,602 audited skills.
What the source does
- FilesystemNone observedNo reads or writes in the source
- NetworkNone observedNo outbound calls in the source
- ShellNone observedNo commands run in the source
- DependenciesPinnedNothing floats
- SecretsNone foundNo keys in source
Five audit layers
| Layer | What we check | Result | Findings |
|---|---|---|---|
L0 Provenance | Repo owner, licence, archive status, activity | PASS | 0 |
L1 Static source | Secrets, path traversal, supply chain, hidden code | NA | 0 |
L2 Instructions | Prompt injection, authority framing, hidden directives | PASS | 0 |
L3 Inventory | The files and declarations match the source | PASS | 0 |
L4 Sandbox | Run in isolation and watch behaviour | SKIPPED why | 0 |
Gates applied: no behavioural pass.
Findings (0)
No findings at any severity. We re-audit when the source changes.
Audit 0.4.1 · source sha a6bc8e8fefb6 · 30 Oct 2026Report an issue or request a re-scan
Provenance
Who published it, and what the verdict is pinned to
- Publisheryaklang GitHub organizationOwner of the repository this skill is read from
- Source folderyaklang/hack-skills/skills/auth-secThe exact folder we audited
- LicenceMITAs the repository states it
- Commit pinned for this verdicta6bc8e8fefb6A new audit runs when the source changes
- Repository statusNot archivedLast push 46 days ago
- Sandboxed runNot runSkills are read, not executed; layer L4 is skipped
What it tells the agent
Full source on GitHub ↗Its description: Entry P1 category router for authentication and authorization. Use when testing login flows, sessions, object authorization, JWT, OAuth, CORS, CSRF, and enterprise SSO weaknesses before any deeper auth topic skill.
--- name: auth-sec description: >- Entry P1 category router for authentication and authorization. Use when testing login flows, sessions, object authorization, JWT, OAuth, CORS, CSRF, and enterprise SSO weaknesses before any deeper auth topic skill. --- # Authentication and Authorization Router This is the routing entry point for authentication, sessions, and authorization boundaries. Use it to decide whether the issue is mainly login mechanics, object-level authorization, browser trust boundaries, or identity protocols such as OAuth/JWT/SAML before going deeper. ## When to Use - The target includes login, registration, password reset, 2FA, sessions, JWT, OAuth, or SSO - You suspect object authorization flaws, cross-tenant access, cross-origin reads, CSRF, or protocol misconfiguration - You need to decide whether to test authentication or authorization first ## Skill Map - [Authentication Bypass](../authbypass-authentication-flaws/SKILL.md): login bypass, password reset, 2FA, enumeration, brute-force protections - [IDOR Broken Object Authorization](../idor-broken-object-authorization/SKILL.md): IDOR, BOLA, BFLA, missing object permissions - [JWT OAuth Token Attacks](../jwt-oauth-token-attacks/SKILL.md): algorithm confusion, key trust issues, claim abuse, token forgery - [OAuth OIDC Misconfiguration](../oauth-oidc-misconfiguration/SKILL.md): redirect URI, state, nonce, PKCE, account binding - [CSRF Cross Site Request Forgery](../csrf-cross-site-request-forgery/SKILL.md): CSRF tokens, SameSite, JSON CSRF, login CSRF - [CORS Cross Origin Misconfiguration](../cors-cross-origin-misconfiguration/SKILL.md): reflected Origin, credentialed cross-origin reads, allowlist bypass - [SAML SSO Assertion Attacks](../saml-sso-assertion-attacks/SKILL.md): assertion wrapping, signature validation, audience, ACS boundaries ## Recommended Flow 1. First confirm the authentication model and session boundaries 2. Then confirm object-level and function-level authorization 3. Then move to token, cross-origin, and protocol details 4. If enterprise federation exists, continue with OAuth, OIDC, or SAML topics ## Related Categories - [api-sec](../api-sec/SKILL.md) - Default credentials, username variants, wordlist sizing, and port focus are consolidated in [authbypass-authentication-flaws](../authbypass-authentication-flaws/SKILL.md)
Excerpt, first 2,362 characters of SKILL.md, verbatim from the audited commit. It is text from someone else’s repository, quoted so you can judge it before your agent reads it.
Install
Pinned to the audited commit a6bc8e8
git clone https://github.com/yaklang/hack-skills git -C hack-skills checkout a6bc8e8fefb6
The author documents no install command, so this uses the repository directly. Our verdict covers commit a6bc8e8fefb6 only.
Works in
The author has not said which agents this skill supports, and we have not tested it in any.
Audit history
Every audit, every source change
- ✓SAFE B 89 / 100
first audit · source
a6bc8e8fefb6
README badge
For maintainers · shows the latest audit
[](https://modelsatlas.com/skills/yaklang/auth-sec/)
The badge shows our verdict and grade for this skill, and links back to this page. It changes when the audit does.
Similar skills
obra/superpowers
Use when creating new skills, editing existing skills, or verifying skills work before deployment
mattpocock/skills
A relentless interview to sharpen a plan or design, which also creates docs (ADR's and glossary) as we go.
mattpocock/skills
Grill the user relentlessly about a plan, decision, or idea. Use when the user wants to stress-test their thinking, or uses any 'grill' trigger phrases.
Add this badge to your README
[](https://modelsatlas.com/skills/yaklang/auth-sec/)
<a href="https://modelsatlas.com/skills/yaklang/auth-sec/"><img src="https://modelsatlas.com/skills/yaklang/auth-sec/badge.svg" alt="ModelsAtlas: SAFE B"></a>
Questions about auth-sec
What does the auth-sec skill do?
Is auth-sec safe to install?
What can auth-sec access on my machine?
How current is this page?
Sources
- github.com/yaklang/hack-skills/tree/main/skills/auth-sec — the audited source at commit a6bc8e8fefb6 and every finding aboveObserved · 30 Oct 2026
Spotted something wrong? Report a correction · Methodology
Keep going in your AI
Opens with this page as the source. We add nothing else to the prompt.
- What does the auth-sec skill do?
- Is auth-sec safe to install?
- What can auth-sec access on my machine?