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-windows-credential-material-exposuregit 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-windows-credential-material-exposure)<a href="https://agentmods.dev/skills/unboundcompute/security-agent-skills/hunting-windows-credential-material-exposure"><img src="https://agentmods.dev/badge/skills/unboundcompute/security-agent-skills/hunting-windows-credential-material-exposure/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-windows-credential-material-exposure"><img src="https://agentmods.dev/badge/skills/unboundcompute/security-agent-skills/hunting-windows-credential-material-exposure.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 | $0.00167 | $0.02078 |
| Opus 5.5 | $0.00067 | $0.00831 |
| Sonnet 5.5 | $0.00033 | $0.00416 |
| Haiku 4.5 | $0.00017 | $0.00208 |
Grade A, and why
hunting-windows-credential-material-exposure 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 Windows credential material exposure: when a secret is readable by the wrong principal
Windows keeps a lot of authentication material on a host: verifiers that let a user log on when the domain is unreachable, passwords for services and scheduled tasks that must start unattended, secrets in a protected store, credentials saved for connections, and live credentials in the memory of processes that authenticated. Each store is meant to be readable only by a specific principal, the account that owns it, the system, or an administrator. The exposure is a store readable by a principal that should not reach it: a weak permission on a file or registry location, an over-privileged token that opens a protected process or store, or storage that protects the secret with a key the wrong account can also derive. The bug is not that the secret exists; it is that a principal below the intended one can read usable material from it. You hunt these by listing where credentials live and checking, for each, which principals can read the material and whether what they read is usable.
When to use
- A Windows host stores authentication secrets and you can enumerate the stores and their permissions.
- A principal may hold a token or privilege that opens a protected credential store or process.
- Service, task, saved-connection, or protected-store secrets may be readable below the intended account.
Scope check
Hunt credential exposure only on hosts you own or are authorized to assess, on non-production or a snapshot, proving a secret is recoverable and usable without authenticating as the victim account beyond the authorization. A recovered credential authenticates as another principal, so keep every probe within scope and handle any recovered material as sensitive. If you can't name the authorization, stop.
The loop
- Establish which principal can actually read usable material from the store first. For each credential store, determine the principal it is meant to be readable by and whether a lower-privileged principal can read it and recover usable secret material, through a weak permission, an over-privileged token, or a protection key the reader can also derive. This is the false-positive killer: a store readable only by the intended account, or one whose contents are bound so the reader cannot derive a usable secret, is not an exposure. Name the reading principal and the usable material before claiming impact.
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 · 167 tokens per session scan A 2875f609d2fe
hunting-windows-credential-material-exposure is a skill published in the GitHub repository UnboundCompute/security-agent-skills (5 stars, last pushed 1mo ago), licensed MIT. It adds 167 tokens to every session and 2,078 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.