OpenShell is a runtime for autonomous AI agents that executes them in sandboxed environments governed by declarative policies. It is used to restrict agents' access to files, credentials, data, and network resources, and the catalogue includes skills and workflows for operating and contributing to it.
Borrowing it
Nothing to install: this file belongs to NVIDIA/OpenShell. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/NVIDIA/OpenShell/main/.agents/skills/sbom/SKILL.mdgit clone --depth 1 https://github.com/NVIDIA/OpenShellWrote 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/nvidia/openshell/sbom)<a href="https://agentmods.dev/skills/nvidia/openshell/sbom"><img src="https://agentmods.dev/badge/skills/nvidia/openshell/sbom/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/nvidia/openshell/sbom"><img src="https://agentmods.dev/badge/skills/nvidia/openshell/sbom.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 | $0.00079 | $0.01372 |
| Opus 5.5 | $0.00032 | $0.00549 |
| Sonnet 5.5 | $0.00016 | $0.00274 |
| Haiku 4.5 | $0.00008 | $0.00137 |
Grade A, and why
sbom 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 18d 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 — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SBOM Generation and License Resolution
Generate CycloneDX SBOMs, resolve missing licenses, and export to CSV for compliance review.
Overview
The OpenShell SBOM tooling produces source-tree CycloneDX JSON SBOMs using Syft, resolves missing or hash-based licenses by querying public registries (crates.io, npm, PyPI), and exports the results to CSV for stakeholder review.
SBOMs are release artifacts only -- they are generated on demand and not committed to the repository. Output lands in deploy/sbom/output/ (gitignored).
Pushed gateway, sandbox, and supervisor images carry an SPDX SBOM and minimal SLSA provenance as OCI attestations. Branch E2E, Release Dev, Release, and Pre-release image binaries embed cargo-auditable metadata, so their image SBOMs include linked Rust crates.
Stable Release builds retain images and attestations in OCI archive artifacts.
Publication copies every platform and attestation to GHCR with preserved digests,
then runs the SBOM verification before updating latest.
Prerequisites
mise installhas been run (installs Syft and other tools)- The repository is checked out at the root
Inspecting an Image SBOM
BuildKit uses its default Syft scanner and attaches one SPDX document per platform. Read one without pulling the image:
docker buildx imagetools inspect ghcr.io/nvidia/openshell/gateway:latest \
--format '{{ json (index .SBOM "linux/amd64").SPDX }}'
Validate the final attestation, requiring a Cargo package for an auditable image:
tasks/scripts/verify-image-sbom.sh ghcr.io/nvidia/openshell/gateway:latest --require-cargo
Inspecting an Auditable Image Binary
Opt into auditable metadata when staging a local image binary:
OPENSHELL_AUDITABLE=1 PREBUILT_ARCH=amd64 \
tasks/scripts/stage-prebuilt-binaries.sh gateway
Scan the staged binary rather than the source tree:
mise x -- syft \
"file:deploy/docker/.build/prebuilt-binaries/amd64/openshell-gateway" \
-o cyclonedx-json
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.
- 18d ago Changed · +4 lines 711b71967940
- 22d ago Changed 5bfca89fe50a
- 1mo ago Changed 427002c8bf10
- 2mo ago Changed · +2 lines c2f235e85ebc
- 2mo ago First seen · 143 lines · 79 tokens per session scan A e9f77318c0a3
sbom is a skill published in the GitHub repository NVIDIA/OpenShell (21,172 stars, last pushed yesterday), licensed Apache-2.0. It adds 79 tokens to every session and 1,372 once invoked, about $0.0003 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 2026-08-30.
sbom compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| sbomNVIDIA/OpenShell | Skill | 21k | yesterday | Apache-2.0 | A | 79 | Claude Code, Codex |
| fto-triageanthropics/claude-for-legal | Skill | 9.9k | 3d ago | Apache-2.0 | A | 81 | Claude Code |
| legal-holdanthropics/claude-for-legal | Skill | 9.9k | 3d ago | Apache-2.0 | A | 68 | Claude Code |
| specification-writingwanshuiyin/Auto-claude-code-research-in-sleep | Skill | 19k | 3d ago | MIT | A | 49 | Claude Code |
| terms-of-servicegenspark-ai/genoffice | Skill | 12k | yesterday | Apache-2.0 | A | 32 | Claude Code, Codex |
| x-scorecardx-cmd/x-cmd | Skill | 4.7k | 6d ago | Apache-2.0 | A | 57 | Claude Code, Codex |
| gesellschaftsrechtliche-satzungen-agbKlotzkette/claude-fuer-deutsches-recht | Skill | 1.8k | today | Apache-2.0 | A | 69 | Claude Code |