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 UnboundCompute/security-agent-skills --skill auditing-declarative-authorizationgit clone --depth 1 https://github.com/UnboundCompute/security-agent-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/unboundcompute/security-agent-skills/auditing-declarative-authorization)<a href="https://agentmods.dev/skills/unboundcompute/security-agent-skills/auditing-declarative-authorization"><img src="https://agentmods.dev/badge/skills/unboundcompute/security-agent-skills/auditing-declarative-authorization.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00111 | $0.01496 |
| Opus 5 | $0.00056 | $0.00748 |
| Sonnet 5 | $0.00022 | $0.00299 |
| Haiku 4.5 | $0.00011 | $0.00150 |
Grade A, and why
auditing-declarative-authorization 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 7d 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 — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Auditing declarative authorization: coverage and correctness are two audits
Modern authorization is often declarative: a policy attached to a table, a filter registered on a controller, a rule in a gateway or serverless config. The strength of that model is also its weakness, security depends on the rule being attached to every path that needs it, and on the rule actually expressing the intended constraint. The failures are gaps (a route the filter never covers) and mis-statements (a rule that checks the wrong thing), and both are invisible if you only read the routes that are protected.
When to use
- You are reviewing role- or policy-driven access control.
- Authorization is enforced by row-level policies, controller filters, middleware, or gateway rules.
- Protection depends on a rule being attached per route, per table, or per resource.
Scope check
Audit access control in systems you own or are authorized to test, with test accounts across roles and tenants. If you can't name the authorization, stop.
The loop
-
Locate every declared rule and its scope. Inventory the authorization rules: row-level policies, controller filters, middleware, gateway or serverless access rules, and ownership checks. For each, determine exactly which paths, tables, or resources it covers. The audit is about coverage and correctness, so start by mapping what each rule protects.
-
Find the paths the rule does not cover. Enumerate every route, query, or resource access and check which are not covered by any rule. A framework filter that must be added per controller is missing wherever a developer forgot it; a policy on one table does not protect a sibling table or a raw query that bypasses the policy layer. The uncovered path is the bug.
-
Check the default of the policy layer. When no rule matches, does access default to deny or allow? A row-level-security system with policies enabled but a permissive fallback, or a gateway that allows unmatched routes, grants access wherever a rule is absent. Confirm the default is deny.
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.
- 7d ago First seen · 129 lines · 111 tokens per session scan A 003b27470e49
auditing-declarative-authorization is a skill published in the GitHub repository UnboundCompute/security-agent-skills (5 stars, last pushed 4d ago), licensed MIT. It adds 111 tokens to every session and 1,496 once invoked, about $0.0006 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 2026-08-31.
Other skills, from other repositories
prodcheck-review
Review this codebase against the prodcheck pre-production checklists — security, performance, scale, integrations and post-launch readiness. Use when asked to check whether a project is ready to ship, to audit an area before launch, or to work through a specific checklist. Produces evidence with file:line citations…
integrate-arcjet-guard-genkit
Integrate Arcjet security into a Genkit JS agent using @arcjet/guard — wrap ai.defineTool, put guardMiddleware on generate({ use }) for unwrapped / MCP / filesystem tools, and read a caller-owned id from generate({ context }). Use when asked to add Arcjet to genkit, rate limit its tools, screen inbound messages, or…
integrate-arcjet-guard-langgraph
Integrate Arcjet security into a LangGraph Graph API agent using @arcjet/guard — wrap tool() / StructuredTool, wrap ToolNode for unwrapped MCP tools, and read threadid for correlation. Use when asked to add Arcjet to a LangGraph StateGraph / ToolNode agent, rate limit its tools, screen inbound messages, or block…
integrate-arcjet-guard-tanstack-ai
Integrate Arcjet security into a TanStack AI chat() app using @arcjet/guard — put guardMiddleware first on chat({ middleware }) so onBeforeToolCall gates tools, and read a caller-owned id from chat({ context }). Use when asked to add Arcjet to TanStack AI, rate limit its tools, screen inbound messages, or block prompt…
integrate-arcjet-guard-claude-managed-agents
Integrate Arcjet security into Claude Managed Agents (hosted REST+SSE, beta managed-agents-2026-04-01) using @arcjet/guard — screen user.message / initialevents before sessions.events.send, and gate custom tools on agent.customtooluse. Use when asked to add Arcjet to Claude Managed Agents, rate limit custom tools, or…
linear-claude-skill
Manage Linear issues, projects, and teams.