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-workload-secret-exposure-surfacegit 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-workload-secret-exposure-surface)<a href="https://agentmods.dev/skills/unboundcompute/security-agent-skills/auditing-workload-secret-exposure-surface"><img src="https://agentmods.dev/badge/skills/unboundcompute/security-agent-skills/auditing-workload-secret-exposure-surface/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/auditing-workload-secret-exposure-surface"><img src="https://agentmods.dev/badge/skills/unboundcompute/security-agent-skills/auditing-workload-secret-exposure-surface.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 | $0.02015 |
| Opus 5.5 | $0.00069 | $0.00806 |
| Sonnet 5.5 | $0.00034 | $0.00403 |
| Haiku 4.5 | $0.00017 | $0.00201 |
Grade A, and why
auditing-workload-secret-exposure-surface 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 — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Auditing workload secret exposure surface: who else can read this secret
A secret a workload needs is safe only if nothing beyond the intended consumer can read it, and containerized delivery quietly widens that set. An environment variable is inherited by every child process, echoed by many debug and introspection endpoints, and captured in crash dumps and process listings, so an env secret is readable by far more than the code that meant to use it. A mounted secret file is readable by every container in the pod that shares the mount, so a sidecar becomes a reader. A secret that lands in a log line or an error message is exposed to whoever reads logs, which is usually a much broader audience than whoever holds the secret. And the orchestrator's secret object is readable by every identity its access rules admit, often more service accounts than the one workload. The audit is not whether the secret exists but who else can see it. You audit this by tracing each secret from its store into the workload and enumerating every other reader.
When to use
- Workloads consume secrets through environment variables, mounted files, or the orchestrator's secret store.
- Sidecars, child processes, debug endpoints, or logs may be able to read a secret meant for one consumer.
- A secret object may be readable by more identities or service accounts than the single workload that needs it.
Scope check
Audit secret exposure only for workloads and clusters you own or are authorized to assess, on non-production secrets. Confirming exposure means reading a real secret through the exposing path, so use non-production credentials and never exfiltrate or reuse a secret you surface. If you can't name the authorization, stop.
The loop
- Establish the intended consumer first. Name, for each secret, the single process or workload that is supposed to read it and nothing else. This is the false-positive killer: a secret delivered as a file mounted only into the one container that needs it, with the secret object readable by only that workload's service account, is correctly scoped. Name the intended consumer, then enumerate every other reader.
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 · 134 lines · 172 tokens per session scan A 5daa5bd36508
auditing-workload-secret-exposure-surface 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 2,015 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.