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-kerberos-and-ad-delegation-abusegit 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-kerberos-and-ad-delegation-abuse)<a href="https://agentmods.dev/skills/unboundcompute/security-agent-skills/hunting-kerberos-and-ad-delegation-abuse"><img src="https://agentmods.dev/badge/skills/unboundcompute/security-agent-skills/hunting-kerberos-and-ad-delegation-abuse/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-kerberos-and-ad-delegation-abuse"><img src="https://agentmods.dev/badge/skills/unboundcompute/security-agent-skills/hunting-kerberos-and-ad-delegation-abuse.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 | $0.00182 | $0.02340 |
| Opus 5.5 | $0.00073 | $0.00936 |
| Sonnet 5.5 | $0.00036 | $0.00468 |
| Haiku 4.5 | $0.00018 | $0.00234 |
Grade A, and why
hunting-kerberos-and-ad-delegation-abuse 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 — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Hunting Kerberos and AD delegation abuse: delegation lets a service become the user, so scope it
Kerberos delegation exists so a front-end service can act as the user against a back-end service, a web app reaching a database as the logged-in user, for instance. That is useful and also a standing impersonation right, and the danger is entirely in its scope. Unconstrained delegation is the worst case: a service with it receives a forwardable ticket for every user who authenticates, caches it, and can replay that ticket against anything, so compromising one such service turns every user who touched it, up to and including a domain admin, into an identity the attacker can wear. Constrained delegation narrows the targets, but if the allowed targets include a higher-privileged service, or protocol transition lets the service request tickets for users who never authenticated to it, the constraint is a ramp. Resource-based constrained delegation moves the setting onto the target object, so an attacker who can write to an object they control can authorize their own delegation into it. And the credential side is just as live: a service account with a service principal name can be Kerberoasted, its ticket requested and the encrypted portion cracked offline to recover a weak password, and an account that does not require pre-authentication is roastable the same way without even authenticating. The hunt inventories delegation rights and roastable accounts and traces each to the highest identity it can reach. You hunt this by finding who may delegate for whom and who can be cracked, then following the chain up.
When to use
- An Active Directory environment uses Kerberos with service accounts, service principal names, and one or more delegation models configured.
- A service may have unconstrained delegation, constrained delegation to a sensitive target, or attacker-settable resource-based delegation.
- A service account may be Kerberoastable through its SPN, or an account may not require Kerberos pre-authentication.
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 · 153 lines · 182 tokens per session scan A 0898c5c8c9e6
hunting-kerberos-and-ad-delegation-abuse is a skill published in the GitHub repository UnboundCompute/security-agent-skills (5 stars, last pushed 1mo ago), licensed MIT. It adds 182 tokens to every session and 2,340 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 2026-09-05.
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.