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 bx33661/oh-my-vul --skill omv-auditgit clone --depth 1 https://github.com/bx33661/oh-my-vulWrote 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/bx33661/oh-my-vul/omv-audit)<a href="https://agentmods.dev/skills/bx33661/oh-my-vul/omv-audit"><img src="https://agentmods.dev/badge/skills/bx33661/oh-my-vul/omv-audit/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/bx33661/oh-my-vul/omv-audit"><img src="https://agentmods.dev/badge/skills/bx33661/oh-my-vul/omv-audit.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 | $0.00088 | $0.02955 |
| Opus 5 | $0.00044 | $0.01477 |
| Sonnet 5 | $0.00018 | $0.00591 |
| Haiku 4.5 | $0.00009 | $0.00296 |
Grade A, and why
omv-audit 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 11d 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 — 177 lines — stays where its author put it; the contents beside it link to each section on GitHub.
omv-audit
深度审计一个 candidate 漏洞发现,填充 Evidence.v1 文件,为 /omv-report 做好准备。
Stay in passive research mode: read public source code only. Do not send requests to live services, do not auto-execute PoC code. Local analysis, static reasoning, and local test descriptions are allowed.
Invocation
/omv-audit <id> [--force]
<id>对应.omv/findings/<id>.yaml文件--force允许重新审计已为 confirmed/blocked 的文件
Reference Loading
按需加载,不要一次性全读:
- 审计方法论与置信度框架:
references/audit-playbook.md - CVSS v3.1 度量决策表:
references/shared/cvss-builder.md - 14 个生态的 PatternPack manifest 位于
references/pattern-packs/,对应 Markdown registry 位于references/patterns/ - Evidence.v1 字段定义与 evidence/submission 评分规则:
contracts/evidence.v1.yaml - ThreatMap.v1 图证据字段:
contracts/threat-map.v1.yaml - Verification.v1 对抗复核 sidecar:
contracts/verification.v1.yaml
审计目标
读取 .omv/findings/<id>.yaml 后,你的目标是将以下字段填写为具体、可验证的值(非 unknown):
必填(confirmed 所需)
versions.tested— 实际测试的版本号evidence.source— 攻击者可控的输入入口(含 file:line)evidence.sink— 危险操作(含 file:line)evidence.guard— 缺失或可绕过的防御(含 file:line 或"不存在"的说明)evidence.reproducer— 本地复现步骤描述evidence.observed_result— 本地运行后实际观测到的结果(若 passive 模式无法在本地执行,保留unknown,在provenance.unverified_fields中列出,交由/omv-repro完成)cvss.vector/cvss.score/cvss.severitydedup.*— NVD/GHSA/生态系统数据库检索结果verdict.*— 当前可利用性判断(proven|plausible|blocked|disproven)、置信度和原因
如何达到目标,由你自主决定。 根据 finding 的实际情况——漏洞类别、已有线索、代码结构——自主选择切入点、阅读哪些文件、花多少精力在每个环节。参考 references/audit-playbook.md 获取思维框架,但不要把它当作执行脚本。
如果 finding 属于任一受支持生态,先加载 references/pattern-packs/ 下对应 JSON,再按需加载 references/patterns/ 下对应 Markdown registry,用其中的 source pattern、sink signature、expected guard、evidence criteria、false-positive checks 和 CWE 映射辅助判断。Pattern registry 是方法论,不是真实漏洞案例库;不要加载无关生态 registry。
当证据链足够清楚时,生成可选 ThreatMap.v1 sidecar,记录 source → transform → sink 的 dataflow 路径:
omv threat-map init <id>
这会在 .omv/threatmaps/<id>.yaml 生成骨架(finding_id 和 package 块已从 finding 填好,paths: [] 留待填写)。然后在每个已确认的 source → sink 路径下补一条 paths[] 条目:source(type/location/description)、transforms[](中间每一步:parse/decode/normalize/validate/authorize)、sink、guard(present/bypassable)、confidence。Schema 见 contracts/threat-map.v1.yaml。ThreatMap 是 Evidence.v1 的补充,不替代 evidence.source / evidence.sink / evidence.guard 摘要字段;sidecar 不修改父 Evidence.v1 文件。填写后运行 omv threat-map validate <id>。
What ships with it
43 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.
- contracts/evidence.v1.yaml 9.1 KB
- contracts/threat-map.v1.yaml 2.7 KB
- contracts/verification.v1.yaml 1019 B
- evals/evals.json 3.6 KB
- evals/golden/confirmed-complete.md 526 B
- evals/golden/critical-ssti.md 689 B
- evals/golden/duplicate-blocked.md 387 B
- evals/golden/guard-bypass.md 653 B
- evals/golden/inaccessible-source.md 575 B
- evals/golden/incomplete-observed-result.md 470 B
- evals/golden/threatmap-path-traversal.md 1.8 KB
- references/audit-playbook.md 4.2 KB
- references/output-contract.md 2.0 KB
- references/pattern-packs/csharp.json 292 B
- references/pattern-packs/dart.json 272 B
- references/pattern-packs/elixir.json 280 B
- references/pattern-packs/go.json 256 B
- references/pattern-packs/java.json 259 B
- references/pattern-packs/lua.json 272 B
- references/pattern-packs/npm.json 298 B
- references/pattern-packs/perl.json 263 B
- references/pattern-packs/php.json 292 B
- references/pattern-packs/python.json 271 B
- references/pattern-packs/r.json 268 B
- references/pattern-packs/ruby.json 278 B
- references/pattern-packs/rust.json 281 B
- references/pattern-packs/swift.json 282 B
- references/patterns/csharp.md 2.6 KB
- references/patterns/dart.md 2.4 KB
- references/patterns/elixir.md 2.4 KB
- references/patterns/go.md 2.3 KB
- references/patterns/java.md 2.2 KB
- references/patterns/lua.md 2.6 KB
- references/patterns/npm.md 2.6 KB
- references/patterns/perl.md 2.4 KB
- references/patterns/php.md 2.6 KB
- references/patterns/python.md 2.4 KB
- references/patterns/r.md 2.6 KB
- references/patterns/ruby.md 2.1 KB
- references/patterns/rust.md 2.2 KB
- references/patterns/swift.md 2.5 KB
- references/shared/cvss-builder.md 3.9 KB
- scripts/check_output.py 3.9 KB runs code
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.
- 11d ago First seen · 177 lines · 88 tokens per session scan A 40dec3d234be
omv-audit is a skill published in the GitHub repository bx33661/oh-my-vul (4 stars, last pushed 22d ago), licensed MIT. It adds 88 tokens to every session and 2,955 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
apple-container
Apple's open-source container CLI to build, run, and manage OCI/Linux containers as lightweight per-container VMs on Apple-silicon macOS — no Docker daemon required. Use when the user mentions the container CLI, "apple container", running or building containers on macOS without Docker/Podman, container run, container…
atlassian
Manage Jira issues and Confluence wiki pages in Atlassian Cloud. Use when: (1) searching/creating/updating Jira issues with JQL, (2) searching/reading/creating Confluence pages with CQL, (3) managing Jira workflows, transitions, and comments, (4) browsing Confluence spaces and page hierarchies. Supports OAuth 2.1 via…
elevenlabs
Convert documents and text to audio using ElevenLabs text-to-speech. Use this skill when the user wants to create a podcast, narrate a document, read aloud text, generate audio from a file, or convert text to speech.
outline
Search, read, and manage Outline wiki documents. Use when: (1) searching wiki for documentation, (2) reading wiki pages or articles, (3) listing wiki collections or documents, (4) creating or updating wiki content, (5) exporting documents as markdown. Works with any Outline wiki instance (self-hosted or cloud).
google-drive
Interact with Google Drive - search files, find folders, list contents, download files, upload files, create folders, move, copy, rename, and trash files. Use when user asks to: search Google Drive, find a file/folder, list Drive contents, download or upload files, create folders, move files, or organize Drive…
playwright-cli
Automates browser interactions for testing and validating your own web applications using playwright-cli. Use when you need terminal-first browser control for navigation, form filling, screenshots, tracing, bound browser sessions, debugging, or generating Playwright test code. Only use against applications you own or…