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-supply-chain-risksgit 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-supply-chain-risks)<a href="https://agentmods.dev/skills/unboundcompute/security-agent-skills/hunting-supply-chain-risks"><img src="https://agentmods.dev/badge/skills/unboundcompute/security-agent-skills/hunting-supply-chain-risks/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-supply-chain-risks"><img src="https://agentmods.dev/badge/skills/unboundcompute/security-agent-skills/hunting-supply-chain-risks.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 | $0.00116 | $0.01546 |
| Opus 5.5 | $0.00046 | $0.00618 |
| Sonnet 5.5 | $0.00023 | $0.00309 |
| Haiku 4.5 | $0.00012 | $0.00155 |
Grade A, and why
hunting-supply-chain-risks 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 — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Hunting supply-chain risks: the code you didn't write but still ship
Your application code can pass every review while the thing you actually ship is compromised, because the supply chain is a second, softer surface: what you pull in, what your build runs, and what your CI is trusted to do. These attacks execute in your build or your users' installs, usually before any code review looks at them. Finding them means auditing resolution, execution, and privilege, not the source.
When to use
- You are reviewing a build pipeline, a dependency manifest, or a lockfile.
- You run or depend on an internal package registry alongside public ones.
- You are auditing a CI/CD configuration, its triggers, and its secrets.
Scope check
Audit builds, registries, and pipelines you own or are authorized to test. Do not publish packages or trigger jobs against systems you do not control; probe name collisions passively. If you can't name the authorization, stop.
The loop
-
Map what the build resolves and runs. List every dependency source (registries, internal and public), how names resolve when both exist, and every step the pipeline executes that is not your reviewed code: install scripts, generated config, third-party actions or plugins, and anything triggered by external input.
-
Check for dependency confusion. For each internal or private package name, can a public registry serve a package of the same name, and would your resolver prefer or fall back to it? An internal name that is unclaimed publicly and resolvable from the public registry is a hijack waiting for a version bump. Confirm scoping, registry pinning, and namespace ownership.
-
Check for typo- and slopsquatting. Are dependency names verified against a known-good source, or copied from documentation, an assistant's suggestion, or memory? A package name a model hallucinated and an attacker then registered (slopsquatting) installs attacker code under a plausible name. Verify every name resolves to the intended, established package, not a lookalike or a freshly published near-name.
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 · 131 lines · 116 tokens per session scan A 439ef8bbd561
hunting-supply-chain-risks is a skill published in the GitHub repository UnboundCompute/security-agent-skills (5 stars, last pushed 1mo ago), licensed MIT. It adds 116 tokens to every session and 1,546 once invoked, about $0.0005 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
terraform-skill
Terraform infrastructure as code best practices.
security-engineer
Security Engineer role bundle for building security into products and infrastructure. Orchestrates code review, pipeline hardening, vulnerability response, and infrastructure review workflows. Auto-invoked when the user needs help with secure development practices, CI/CD security, vulnerability management, or…
pipeline-security
Reviews CI/CD pipeline configurations against SLSA v1.0 build levels and OWASP Top 10 CI/CD Security Risks. Auto-invoked when reviewing GitHub Actions workflows, GitLab CI configs, Jenkins pipelines, or when discussing supply chain security. Produces a pipeline security assessment with SLSA level determination and…
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-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…