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 MingyiSecLab/Mingyi-Atlas --skill supplychaingit clone --depth 1 https://github.com/MingyiSecLab/Mingyi-AtlasWrote 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/mingyiseclab/mingyi-atlas/supplychain)<a href="https://agentmods.dev/skills/mingyiseclab/mingyi-atlas/supplychain"><img src="https://agentmods.dev/badge/skills/mingyiseclab/mingyi-atlas/supplychain/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/mingyiseclab/mingyi-atlas/supplychain"><img src="https://agentmods.dev/badge/skills/mingyiseclab/mingyi-atlas/supplychain.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 | $0.00031 | $0.00569 |
| Opus 5 | $0.00015 | $0.00284 |
| Sonnet 5 | $0.00006 | $0.00114 |
| Haiku 4.5 | $0.00003 | $0.00057 |
Grade A, and why
supplychain scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
This is a copy
94% identical to supplychain-overview — 4 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
Supply-Chain Exploitation — Category Overview
This is a routing skill for supply-chain attack research. Sub-skills cover specific techniques against the dependency, build, and distribution layers.
Sub-Skills
| Sub-Skill | Covers | When to Load |
|---|---|---|
| dep-confusion | Public-registry impersonation of private package names, scoped-package abuse (@org/pkg), internal-name OSINT (lockfiles, GitHub Actions, Dockerfiles, error pages) |
Target uses private npm/PyPI/RubyGems/Cargo registries and you've discovered internal package names in public artifacts |
Surface Discovery
# Lockfiles often expose private package names that aren't on public registry
grep -hE '"name":|"@.+/' package-lock.json yarn.lock pnpm-lock.yaml | sort -u
# pip
grep -E '^[a-z0-9_-]+' requirements.txt
# go.mod
grep '^\s*[a-z0-9./_-]\+\s' go.mod
# Maven
grep -A1 '<artifactId>' pom.xml | grep -v '^--$'
Decision Notes
- Always confirm scope authorization in writing before publishing any package, even a benign one, to a public registry. Some bounty programs explicitly disallow public-registry submissions.
- Use a beacon-only payload (DNS callback, HTTPS GET) for confirmation; never ship code that mutates the target environment without an explicit follow-up authorization.
- Real damage from confusion attacks is usually post-install scripts (
postinstall,setup.py install) — focus PoCs on benign callbacks, not RCE. - For build-pipeline poisoning (workflow injection, branch protection bypass) see
/skills/standard/exploit/ad-exploitation/SKILL.md(CI-as-AD-equivalent paths) and the broader threat-modeling under/skills/shared/opsec/SKILL.md.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 9d ago First seen · 41 lines · 31 tokens per session scan A 6bd9c9db25f6
supplychain is a skill published in the GitHub repository MingyiSecLab/Mingyi-Atlas (11 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 31 tokens to every session and 569 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 94% identical to supplychain-overview, differing in 4 lines, and is treated as a copy.
Other skills, from other repositories
cis-aws-foundations-6.5
Ensure the default security group of every VPC restricts all traffic.
cis-aws-foundations-4.3
Ensure AWS Config is enabled in all regions.
cis-aws-foundations-2.1.3
Ensure Organizations management account is not used for workloads.
cis-aws-foundations-2.5
Ensure MFA is enabled for the 'root' user account.
cis-aws-foundations-2.7
Eliminate use of the 'root' user for administrative and daily tasks.
cis-aws-foundations-4.4
Ensure that server access logging is enabled on the CloudTrail S3 bucket.