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-iac-module-and-provider-supply-chaingit 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-iac-module-and-provider-supply-chain)<a href="https://agentmods.dev/skills/unboundcompute/security-agent-skills/auditing-iac-module-and-provider-supply-chain"><img src="https://agentmods.dev/badge/skills/unboundcompute/security-agent-skills/auditing-iac-module-and-provider-supply-chain/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-iac-module-and-provider-supply-chain"><img src="https://agentmods.dev/badge/skills/unboundcompute/security-agent-skills/auditing-iac-module-and-provider-supply-chain.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 | $0.00169 | $0.01956 |
| Opus 5 | $0.00084 | $0.00978 |
| Sonnet 5 | $0.00034 | $0.00391 |
| Haiku 4.5 | $0.00017 | $0.00196 |
Grade A, and why
auditing-iac-module-and-provider-supply-chain 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 12d 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 — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Auditing IaC module and provider supply chain: when planning runs someone else's code
Infrastructure-as-code feels declarative, but modules and providers are code, and they run with the credentials of whoever plans or applies them, which in a pipeline is usually a highly privileged identity. That makes the module and provider supply chain a direct path to those credentials. A module sourced from an unpinned reference can change under you between runs; a provider or plugin pulled without integrity verification can be swapped at the registry; a module that shells out or fetches remote content during planning executes on the runner before anyone reviews an apply; and a lockfile that is absent or not enforced lets the resolved versions drift. The declarative surface hides that a plan is an execution. You audit this by finding where module and provider code enters and whether its source and integrity are pinned.
When to use
- Infrastructure is built from third-party or shared modules and from providers pulled at init time.
- Module sources or provider versions are unpinned, or a dependency lockfile is missing or unenforced.
- Plan or apply runs in CI with a privileged identity, so executing module code reaches real credentials.
Scope check
Audit IaC supply chain only for infrastructure and pipelines you own or are authorized to assess, on non-production state. Confirming that a module executes at plan time runs code on the runner, so keep any proof benign and inside the authorized pipeline. If you can't name the authorization, stop.
The loop
-
Establish the apply identity and its power first. Name the credentials that plan and apply run under and what they can do in the environment. This is the false-positive killer that sets severity: an unpinned module matters far more when apply holds broad cloud permissions than when it is tightly scoped. Name the identity, then trace what code runs under it.
-
Inventory every module and provider source. List where each module comes from (a registry, a version- control reference, a local path) and every provider or plugin the configuration pulls. Each external source is code that will run under the apply identity. Distinguish first-party internal modules from third-party ones, since the trust question differs.
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.
- 12d ago First seen · 133 lines · 169 tokens per session scan A 9358d824ff5b
auditing-iac-module-and-provider-supply-chain is a skill published in the GitHub repository UnboundCompute/security-agent-skills (5 stars, last pushed 4d ago), licensed MIT. It adds 169 tokens to every session and 1,956 once invoked, about $0.0008 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.