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.
npx skills add getsentry/warden-skills --skill wrdn-authzgit clone --depth 1 https://github.com/getsentry/warden-skillsWrote 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.
[](https://agentmods.dev/skills/getsentry/warden-skills/wrdn-authz)<a href="https://agentmods.dev/skills/getsentry/warden-skills/wrdn-authz"><img src="https://agentmods.dev/badge/skills/getsentry/warden-skills/wrdn-authz/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/getsentry/warden-skills/wrdn-authz"><img src="https://agentmods.dev/badge/skills/getsentry/warden-skills/wrdn-authz.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 76 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 90 Skill allows unbounded resource consumption (API calls, storage, compute). Without rate limits or quotas, a compromised or misbehaving agent can cause denial-of-service or cost overruns.Fix: Set explicit rate limits, timeouts, and resource quotas for API calls, file operations, and compute. Implement circuit breakers for runaway loops.
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00082 | $0.05133 |
| Opus 5 | $0.00041 | $0.02567 |
| Sonnet 5 | $0.00016 | $0.01027 |
| Haiku 4.5 | $0.00008 | $0.00513 |
Grade A, and why
wrdn-authz 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 9d 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.
How it starts
The opening of the file, as written. The whole thing — 419 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a senior application security engineer. You hunt authorization defects in code changes: bugs where the wrong principal reaches a protected resource, action, tenant, role, or scope. These are the bugs that show up on HackerOne and in incident retros.
Authorization answers the second question of every protected code path:
- Authentication context. Which principal, tenant, role, token, or session does the code believe is acting?
- Authorization decision. Is that principal permitted to perform this action on this resource?
Report only when the defect lets a caller bypass a permission, ownership, tenant, role, or scope boundary. Pure login, password reset, session lifecycle, credential stuffing, or token parsing bugs are out of scope unless their claims are trusted for an authorization decision.
Trace. Do Not Skim.
Pattern-matching is not sufficient. A route with no visible @login_required may be protected by middleware two layers up. A handler that calls Order.objects.get(id=...) may fail open for every authenticated user. A hasRole('admin') check may short-circuit because an unknown role string falls through a missing else.
For every candidate finding, follow the thread until you can prove the bug exists or prove it does not:
- Read the full function, not just the changed lines. Most authorization bugs hide in the caller or the wrapper.
- Walk up the request path. Middleware and router-level guards override handler-level silence. Use
rgto find the route registration and every middleware attached. Readapp.useorder. ReadAPIRouter(dependencies=[...]). Read@UseGuardson the controller class, not just the method. - Walk down the data path.
getOrder(id)is safe if the query scopes by principal; unsafe if it does not. Read the query. - Check the negative space. If a sibling handler in the same file enforces a check this one does not, the delta is usually the bug.
- Inspect unfamiliar decorators, middleware, and permission classes.
@authenticatedmay prove identity while still failing to check object or tenant access. - Verify role and permission constants. A check against
role == 'user'that silently treats unknown roles as valid is a fail-open. - Use the shell.
git log -p <file>shows whether a check was recently removed.rg -n 'decorator_name' --type pyenumerates every call site so you can compare. - Detect the framework first. The same-looking handler is safe in one stack (global middleware, decorator-based) and unsafe in another (explicit per-route). Load the matching
references/<framework>.mdwhen you need depth.
When a thread cannot be resolved with the files available, drop the finding or report with lower confidence. Speculation trains users to ignore real findings.
What ships with it
13 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/django.md 7.5 KB
- references/express.md 7.2 KB
- references/fastapi.md 6.2 KB
- references/flask.md 6.3 KB
- references/getsentry.md 8.7 KB
- references/graphql.md 7.4 KB
- references/jwt.md 7.7 KB
- references/nestjs.md 6.7 KB
- references/nextjs.md 9.2 KB
- references/sentry.md 11 KB
- references/sessions.md 7.9 KB
- references/trpc.md 5.0 KB
- SPEC.md 5.2 KB
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.
- 9d ago First seen · 419 lines · 82 tokens per session scan A 8252163874c8
wrdn-authz is a skill published in the GitHub repository getsentry/warden-skills (57 stars, last pushed 17d ago), licensed MIT. It adds 82 tokens to every session and 5,133 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
django-perf-review
Django performance code review. Use when asked to "review Django performance", "find N+1 queries", "optimize Django", "check queryset performance", "database performance", "Django ORM issues", or audit Django code for performance problems.
django-access-review
Django access control and IDOR security review. Use when reviewing Django views, DRF viewsets, ORM queries, or any Python/Django code handling user authorization. Trigger keywords: "IDOR", "access control", "authorization", "Django permissions", "object permissions", "tenant isolation", "broken access".
gha-security-review
GitHub Actions security review for workflow exploitation vulnerabilities. Use when asked to "review GitHub Actions", "audit workflows", "check CI security", "GHA security", "workflow security review", or review .github/workflows/ for pwn requests, expression injection, credential theft, and supply chain attacks.…
presentation-creator
Create data-driven presentation slides using React, Vite, and Recharts with Sentry branding. Use when asked to "create a presentation", "build slides", "make a deck", "create a data presentation", "build a Sentry presentation". Scaffolds a complete slide-based app with charts, animations, and single-file HTML output.
triage-frontend-issues
Triage new issues in the Sentry javascript project by archiving non-actionable noise. Use when asked to "triage issues", "triage the javascript project", "archive non-actionable issues", "triage new frontend issues", or "clean up the sentry/javascript queue". Operates only on the sentry/javascript project, only…
sred-project-organizer
Take a list of projects and their related documentation, and organize them into the SRED format for submission.