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 jd-opensource/JoySafeter --skill pentest-supply-chaingit clone --depth 1 https://github.com/jd-opensource/JoySafeterWrote 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/jd-opensource/joysafeter/pentest-supply-chain)<a href="https://agentmods.dev/skills/jd-opensource/joysafeter/pentest-supply-chain"><img src="https://agentmods.dev/badge/skills/jd-opensource/joysafeter/pentest-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/jd-opensource/joysafeter/pentest-supply-chain"><img src="https://agentmods.dev/badge/skills/jd-opensource/joysafeter/pentest-supply-chain.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00028 | $0.00530 |
| Opus 5 | $0.00014 | $0.00265 |
| Sonnet 5 | $0.00006 | $0.00106 |
| Haiku 4.5 | $0.00003 | $0.00053 |
Grade A, and why
pentest-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 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.
How it starts
The opening of the file, as written. The whole thing — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pentest Supply Chain
Purpose
Supply chain attacks (SolarWinds, Log4Shell, xz-utils) are the fastest-growing threat category. Shannon explicitly excludes "vulnerable third-party libraries." MITRE ATT&CK T1195 has zero coverage in any existing skill.
Prerequisites
Authorization Requirements
- Written authorization with supply chain testing scope
- Repository access for dependency and CI/CD analysis
- Registry awareness — confirm which private registries are in use
- Build system access for pipeline review (if white-box)
Environment Setup
- Snyk CLI for dependency vulnerability scanning
- npm audit / pip-audit for ecosystem-specific checks
- Trivy for container and filesystem scanning
- socket.dev for dependency risk analysis
Core Workflow
- Dependency Audit: Analyze package.json/requirements.txt/go.mod for known vulnerable versions, unmaintained packages, suspicious dependencies.
- Dependency Confusion: Check if internal package names can be claimed on public registries (npm, PyPI). Test namespace squatting.
- CI/CD Pipeline Security: Review GitHub Actions/GitLab CI for injection via PR titles/branch names, secrets in logs, unpinned action versions, runner escape.
- Build Artifact Integrity: Verify signatures on containers/packages, check for unsigned artifacts, test image tag mutability.
- Lockfile Integrity: Detect lockfile injection (manipulated resolved URLs), verify lockfile-to-manifest consistency.
- Install Script Abuse: Identify packages with install hooks executing arbitrary code, test typosquatting candidates.
- SBOM Generation: Generate Software Bill of Materials and map transitive dependency risk with CVE correlation.
Tool Categories
| Category | Tools | Purpose |
|---|---|---|
| Dependency Scanning | Snyk, npm audit, pip-audit | Known CVE detection |
| Container Scanning | Trivy, Grype | Image vulnerability analysis |
| Dependency Risk | socket.dev, Semgrep | Behavioral risk analysis |
| CI/CD Review | custom scripts, actionlint | Pipeline security audit |
| SBOM | syft, cyclonedx-cli | Bill of materials generation |
What ships with it
2 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.
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 · 47 lines · 28 tokens per session scan A 9c1f2bb0e635
pentest-supply-chain is a skill published in the GitHub repository jd-opensource/JoySafeter (307 stars, last pushed 4d ago), licensed Apache-2.0. It adds 28 tokens to every session and 530 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
skill-authoring
Author SKILL.md skills: frontmatter, validator limits, structure.
swarmclaw
AI agent runtime and multi-agent orchestration platform. Teaches agents how to use SwarmClaw's 6 primitive tools, persistent memory, dreaming, delegation, connectors, credentials, and the skill system. Use when an agent is running on SwarmClaw and needs to understand the platform's capabilities.
github-operations
Class-level workflow for GitHub repository, issue, pull request, CI, release, authentication, and remote/credential recovery tasks via gh and git. Use when asked to manage GitHub issues/PRs/runs/repos, inspect CI, call gh api, fix broken gh login, recover HTTPS/SSH credential failures, or repair git remotes.
webhook-subscriptions
Webhook subscriptions: event-driven agent runs.
deployment-patterns
Deployment workflows, CI/CD pipeline patterns, Docker containerization, health checks, rollback strategies, and production readiness checklists for web applications.
enterprise-agent-ops
Operate long-lived agent workloads with observability, security boundaries, and lifecycle management.