supply-chain-audit

supply-chain-audit is a skill for Codex from Agent-Hellboy/mcp-runtime. It costs 90 tokens per session (2,344 once invoked), scanned A, original, Apache-2.0.

A security audit process for software and services that enter a build, including Go modules, container images, base images, software inventories, signatures, licenses, and GitHub Actions. A software inventory lists the components included in a build.

In plain words
What is it for?
Checking Go dependencies, Docker images, software inventories, signed artifacts, action pinning, and pull-request workflows.
Why use it?
It helps find vulnerable or unsigned build inputs, license problems, weak workflow protections, and risks from untrusted code changes.

Skill for Codex

Written for Codex: agents/openai.yaml present. Also seen: mentions Codex.

Not installable on its own: it runs a file from its repository that does not travel with it. Clone the repository, or install whatever ships that file. The line is bash hack/trivy-sentinel-images.sh.

Install

Getting it into your agent

There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.

Made for: Codex.

Wrote 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.

agentmods badge for supply-chain-audit

README.md
[![agentmods](https://agentmods.dev/badge/skills/agent-hellboy/mcp-runtime/supply-chain-audit.svg)](https://agentmods.dev/skills/agent-hellboy/mcp-runtime/supply-chain-audit)
Your own site
<a href="https://agentmods.dev/skills/agent-hellboy/mcp-runtime/supply-chain-audit"><img src="https://agentmods.dev/badge/skills/agent-hellboy/mcp-runtime/supply-chain-audit.svg" alt="Measured on agentmods" height="20"></a>
Per session 90 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,344 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00090 $0.02344
Opus 5 $0.00045 $0.01172
Sonnet 5 $0.00018 $0.00469
Haiku 4.5 $0.00009 $0.00234

Measured 6d ago against content hash 8691de00e09e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

supply-chain-audit scanned grade A with 1 finding 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 6d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

`RUN curl ... | sha256sum -c` style).
.codex/skills/supply-chain-audit/SKILL.md · 210 lines

How it starts

The opening of the file, as written. The whole thing — 210 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Supply Chain Audit

Overview

Use this skill to audit everything that crosses the trust boundary into the build: Go modules, container base images, image signatures, SBOMs, and GitHub Actions. Scope intentionally excludes runtime authn/z, RBAC, and cluster posture — those live in security-audit-platform and k8s-hardening-audit.

Findings use the shared template at ../_shared/FINDINGS-TEMPLATE.md.

Step 1 — Inventory the build inputs

  • Go modules: go list -m -json all > /tmp/go-mods.json from repo root and from each services/<name>/ with its own go.mod.
  • Images built by this repo: collect Dockerfile paths.
    find . -name 'Dockerfile*' -not -path './inspirations/*' -not -path './node_modules/*'
    
  • GitHub Actions workflows: ls .github/workflows/.
  • Reusable composite actions: find . -path '*/.github/actions/*' -name action.yml -o -name action.yaml.
  • Pre-commit hook versions: .pre-commit-config.yaml.

State the inventory in the report so a future audit knows the surface.

Step 2 — Vulnerable Go dependencies

govulncheck reports CVEs the binary actually reaches, not just modules in the graph. Run from every Go module root:

go install golang.org/x/vuln/cmd/govulncheck@latest

govulncheck ./...
for d in services/*/; do
  [ -f "$d/go.mod" ] && (cd "$d" && govulncheck ./...)
done

Report each Vulnerability block as a finding with severity drawn from the upstream advisory and the CallStack field as exploitability evidence.

Step 3 — Container image scans

Mirror .github/workflows/security-trivy.yaml locally. Build every image the repo produces and scan it as an image (filesystem scans miss base-image CVEs). Pin the same Trivy action version (currently 0.36.0aquasecurity/trivy-action@ed142fd0673e97e23eac54620cfb913e5ce36c25):

docker build --pull -f Dockerfile.operator -t mcp-runtime-operator:audit .
docker build --pull -f services/platform-api/Dockerfile -t mcp-platform-api:audit .
docker build --pull -f services/analytics-api/Dockerfile -t mcp-analytics-api:audit .
docker build --pull -f services/runtime-api/Dockerfile -t mcp-runtime-api:audit .
docker build --pull -f services/platform-api/Dockerfile -t mcp-platform-api:audit .
docker build --pull -f services/runtime-api/Dockerfile -t mcp-runtime-api:audit .
docker build --pull -f services/analytics-api/Dockerfile -t mcp-analytics-api:audit .
docker build --pull -f services/ui/Dockerfile -t mcp-sentinel-ui:audit .
docker build --pull -f services/ingest/Dockerfile -t mcp-sentinel-ingest:audit .
docker build --pull -f services/processor/Dockerfile -t mcp-sentinel-processor:audit .
docker build --pull -f services/mcp-gateway/Dockerfile -t mcp-sentinel-mcp-gateway:audit .

# Or use the repo helper (same image set + CI-matching flags):
bash hack/trivy-sentinel-images.sh

for img in mcp-runtime-operator:audit mcp-platform-api:audit mcp-runtime-api:audit \
           mcp-analytics-api:audit mcp-sentinel-ui:audit \
           mcp-sentinel-ingest:audit mcp-sentinel-processor:audit \
           mcp-sentinel-mcp-gateway:audit; do
  trivy image --exit-code 0 --severity CRITICAL,HIGH --ignore-unfixed \
              --vuln-type os,library --format table "$img"
done

Read the full file on GitHub · 210 lines

Files

What ships with it

3 files 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.

Changes

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.

  1. 6d ago First seen · 210 lines · 90 tokens per session scan A 8691de00e09e

Subscribe to this mod's changes

supply-chain-audit is a skill published in the GitHub repository Agent-Hellboy/mcp-runtime (6 stars, last pushed 3d ago), licensed Apache-2.0. It adds 90 tokens to every session and 2,344 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

competition-agent-cloud

Internal downstream skill for ctf-sandbox-orchestrator. CTF-sandbox workflow for AI-agent, prompt-injection, MCP or toolchain, cloud, container, CI/CD, and supply-chain challenges. Use when the user asks to analyze prompt-to-tool flows, retrieval poisoning, mounted secrets, deployment drift, runtime-vs-manifest…

xAmirHamza77/ReverseOps-Skill · 107 tokens

competition-supply-chain

Internal downstream skill for ctf-sandbox-orchestrator. CTF-sandbox workflow for CI/CD, registry, dependency drift, artifact provenance, image build, release pipeline, and runtime consumer challenges. Use when the user asks to trace dependency drift, registry pulls, malicious packages, build or release tampering, CI…

xAmirHamza77/ReverseOps-Skill · 103 tokens

konflux-build

Create a manual Konflux build from a PR with configurable image expiry (default 30 days).

openshift/hypershift · 23 tokens

performing-container-security-scanning-with-trivy

Scan container images, filesystems, and Kubernetes manifests for vulnerabilities, misconfigurations, exposed secrets, and license compliance issues using Aqua Security Trivy with SBOM generation and CI/CD integration.

xalgorix/xalgorix · 48 tokens

devops

DevOps - Docker, CI/CD, cloud infra, monitoring.

sipyourdrink-ltd/bernstein · 16 tokens

devops-infrastructure

Guides Docker, CI/CD pipelines, deployment strategies, infrastructure as code, and observability setup. Use when writing Dockerfiles, configuring GitHub Actions, planning deployments, setting up monitoring, or when asked about containers, pipelines, Terraform, or production infrastructure.

CloudAI-X/claude-workflow-v2 · 57 tokens