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 hunting-active-directory-acl-abuse-pathsgit 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/hunting-active-directory-acl-abuse-paths)<a href="https://agentmods.dev/skills/unboundcompute/security-agent-skills/hunting-active-directory-acl-abuse-paths"><img src="https://agentmods.dev/badge/skills/unboundcompute/security-agent-skills/hunting-active-directory-acl-abuse-paths/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/unboundcompute/security-agent-skills/hunting-active-directory-acl-abuse-paths"><img src="https://agentmods.dev/badge/skills/unboundcompute/security-agent-skills/hunting-active-directory-acl-abuse-paths.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00172 | $0.02125 |
| Opus 5.5 | $0.00069 | $0.00850 |
| Sonnet 5.5 | $0.00034 | $0.00425 |
| Haiku 4.5 | $0.00017 | $0.00213 |
Grade A, and why
hunting-active-directory-acl-abuse-paths 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 1mo 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 — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Hunting Active Directory ACL abuse paths: when one granted right owns a privileged account
Every object in an Active Directory carries an access control list, and the rights on it decide who may change it. Most of those rights are mundane, but a handful hand control of the object to whoever holds them: the right to reset a password logs you in as that account, the right to write group membership adds you to a privileged group, a generic write lets you set a logon script or a delegation the account will honor, and taking ownership lets you rewrite the permissions to grant yourself anything. When one of these rights sits on a privileged object and is held by a low-privileged principal, that principal owns the object; when the object it then controls holds a right over a further object, the control chains. The bug is a right over a more privileged object held by a principal who should not control it. You hunt these by reading the permissions on privileged objects and tracing each dangerous right to the account it seizes.
When to use
- Directory object permissions may grant a standard user a write over a privileged user, group, or computer.
- A delegated-control grant on an organizational unit may reach objects more privileged than the grantee.
- A chain of object rights may lead from a low-privileged principal to a privileged account.
Scope check
Test object-permission abuse only in directories you own or are authorized to assess, on non-production or a lab domain, making only reversible changes to test objects you are permitted to modify and never seizing a real privileged account outside the authorization. A confirmed chain yields control of a privileged account, so keep every probe within scope. If you can't name the authorization, stop.
The loop
- Establish which dangerous right the low-privileged principal actually holds over a privileged object first. For each privileged object, read its permissions and determine whether a low-privileged principal holds a right that seizes control: reset-password, write-membership, a generic write, write-owner, or take-ownership. This is the false-positive killer: a right to read the object, or a write over an object no more privileged than the principal, is not an escalation. Name the specific right and the object it controls before claiming a path.
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.
- 1mo ago First seen · 139 lines · 172 tokens per session scan A 9a03666855c4
hunting-active-directory-acl-abuse-paths is a skill published in the GitHub repository UnboundCompute/security-agent-skills (5 stars, last pushed 1mo ago), licensed MIT. It adds 172 tokens to every session and 2,125 once invoked, about $0.0007 per session on Opus 5.5. 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 2026-09-09.
Other skills, from other repositories
prodcheck-review
Review this codebase against the prodcheck pre-production checklists — security, performance, scale, integrations, post-launch readiness and people. 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…
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-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.
varlock-claude-skill
Secure environment variable management ensuring secrets are never exposed in Claude sessions, terminals, logs, or git commits.