Skip to content
Skills Library
Security · Review & audit

auth

/auth

Auth & identity security lens. Use on any task touching login, signup, OAuth, OIDC, SAML, sessions, cookies, JWT, password reset, MFA, and when the user says "doberman" or asks if this is safe. Defensive use only.

Repository
watchdog ↗
Licence
MIT
Last repository change
03.11.2026

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 03.11.2026, without references to retired models or APIs.

Licence

MIT, open: use and modify while retaining author attribution.

What it does and when to use it

Auth & identity security lens. Use on any task touching login, signup, OAuth, OIDC, SAML, sessions, cookies, JWT, password reset, MFA, and when the user says "doberman" or asks if this is safe. Defensive use only.

Triggers from the description

doberman
Original author description

Auth & identity security lens. Use on any task touching login, signup, OAuth, OIDC, SAML, sessions, cookies, JWT, password reset, MFA, and when the user says "doberman" or asks if this is safe. Defensive use only.

How it works

  1. Active every turn
  2. What to look for (in order)
  3. Rules of engagement
Original SKILL.md headings · 24 lines, 232 words
SKILL.md preview
---
name: auth
description: Auth & identity security lens. Use on any task touching login, signup, OAuth, OIDC, SAML, sessions, cookies, JWT, password reset, MFA, and when the user says "doberman" or asks if this is safe. Defensive use only.
---

# Auth & identity dog

You are a careful auth security reviewer. You find real weaknesses in work the user is responsible for and explain the fix in plain words.

## Active every turn
For each risky spot say: **finding + `file:line` + why it's exploitable + smallest fix**. No filler.

## What to look for (in order)
1. **Credentials** — weak hashing (MD5/SHA1/unsalted), no rate limit or lockout, user enumeration via messages or timing.
2. **Sessions** — cookies without Secure/HttpOnly/SameSite, no rotation on login, no server-side logout, long-lived tokens.
3. **JWT** — decode without verify, `alg: none`/HS-RS confusion, no expiry, secrets in code.
4. **OAuth/OIDC** — missing `state`/PKCE, open redirect_uri, token in URL fragment logs, id_token not validated (iss/aud/nonce).
5. **Password reset** — guessable or non-expiring tokens, token in response, no invalidation after use.
6. **MFA** — bypassable step, recovery codes in plaintext, MFA not enforced on sensitive actions.
7. **Account linking and SSO** — email-based auto-linking, unverified emails trusted.

## Rules of engagement
- Static review only. Never change live systems or send traffic to targets outside the user's written scope.
- Never print a secret's value — not keys, tokens or passwords, even weak defaults. Give file:line and the secret type only.
- End each review with: what you did **not** check, and the top risk the user must act on.

Off: user says "stop doberman" or "normal mode".

Versions

RepositoryScoreLicence
This page · watchdoglab/watchdog90MIT
mixpanel/mixpanel-headless100MIT
microsoft/apm100MIT
microsoft/apm100MIT
EpicenterHQ/epicenter100MIT
pawangai/pawang-agents100MIT
felipefontoura/bento100MIT
tomaspozo/agentlink100MIT
githubnext/apm100MIT

Database snapshot: 13.11.2026 · package version 86a5017d119a (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

  • 100watchdog-go-auth
    On-demand auth audit (Login, OAuth/OIDC, sessions, password reset, MFA, JWT, SSO). Use for /watchdog-go-auth. Defensive use only.
  • 90authentication-security
    Review and harden authentication in a SaaS application — login, registration, password storage, sessions and cookies, JWT/API tokens, MFA, OAuth/SSO and account recovery. Use when touching auth code or auditing identity flows.
  • 95identity-access-control
    Use this capability for login, signup, session management, OAuth/OIDC, SSO, JWT, cookies, MFA, RBAC, ABAC, ReBAC, permission checks, service identities, and access reviews. Trigger on auth, login, signup, token, JWT, OAuth, OIDC, SSO, session, cookie, role, permission, MFA, 2FA,…
  • 91secure-auth
    Secure authentication patterns (OWASP, NIST). Use for login, registration, password reset, sessions, JWT, OAuth, MFA, passkeys.
  • 90auth-session-and-oauth
    Use when a ticket touches how a user proves who they are — login, logout, sessions, cookies, JWTs, refresh tokens, password reset, OAuth/OIDC sign-in with a provider, API keys — and the implementation must use the repo's existing auth library and the platform's primitives…
  • 90auth-mechanism-review
    Reasons about authentication weaknesses (JWT flaws, session security, OAuth and OIDC flaws, brute-force surfaces, password storage) from code and docs evidence. Use when docs or route inventories describe login, sessions, token handling, OAuth callbacks, password reset or MFA.

Feedback and reports

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