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 AbyssCN/oh-my-dag --skill omd-auditgit clone --depth 1 https://github.com/AbyssCN/oh-my-dagWrote 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/abysscn/oh-my-dag/omd-audit)<a href="https://agentmods.dev/skills/abysscn/oh-my-dag/omd-audit"><img src="https://agentmods.dev/badge/skills/abysscn/oh-my-dag/omd-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/abysscn/oh-my-dag/omd-audit"><img src="https://agentmods.dev/badge/skills/abysscn/oh-my-dag/omd-audit.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 | $0.00080 | $0.00963 |
| Opus 5 | $0.00040 | $0.00481 |
| Sonnet 5 | $0.00016 | $0.00193 |
| Haiku 4.5 | $0.00008 | $0.00096 |
Grade A, and why
omd-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.
What it actually says
/omd-audit — 安全专项审计
经 omd MCP 的 run(未加载先 ToolSearch "run")派一张多视角安全审查 DAG:每个信任边界维度一个并行节点,末节点汇总去重成按严重度排序的报告。只查安全,通用正确性走 /omd-review,规则扫描走 /omd-sast。
用法
run 的 task 按此模板(按目标裁剪维度),优先扫外部输入入口:路由/接口层、回调/webhook、消息入口、SQL/schema。
对 <目标路径/模块> 做安全审计, 每维度一个并行节点, 末节点汇总去重成结构化报告。
按下方「信任边界清单」逐条查, 每 finding: file:line + 攻击场景 + 严重度(P0/P1/P2) + 修复建议。
三段式:拿 runId → dag_status 轮询(别重复发起)→ dag_result 取报告。DAG 产出是候选,你负责终审:对每个可疑项读代码证实攻击路径可达,再定性——证不出可达的降级或剔除。
信任边界清单(逐条查)
- 验签:HMAC / 签名校验用恒时比较(
timingSafeEqual),不是===(防时序侧信道);签名缺失即拒。 - 认证 gap:每个改状态的入口有鉴权闸;
GET只读、不改状态;无「存在性泄露」(用返回码/时延区分资源存不存在)。 - 注入:命令 / SQL / 路径 由外部输入拼接 → 参数化或净化;禁裸 shell 字符串拼接;SQL 用绑定参数不用字符串拼。
- fail-open:
catch { return null }/ 吞错后继续 = 校验失败却放行。审所有 catch:失败必须拒绝(fail-closed),不是静默通过。 - 不安全默认值:默认开放 / 默认信任 / 默认 admin;开关缺省应最小权限。
- 秘密与泄漏:硬编码 key/token、日志打印凭证或 PII、不安全存储。
- 越权与隔离:行级/租户隔离默认 deny;缺失的所有权校验(改别人的资源)。
- 反序列化 / 供应链:不可信数据反序列化、危险依赖用法、不安全临时文件。
untrusted 入口校验覆盖率
单列一个节点扫所有接受外部输入的入口(路由 body / 回调 / 消息):
- PROTECTED = 入口处有结构化 schema 校验(如
safeParse);UNPROTECTED = 收外部输入却无校验。 - 输出:覆盖率表 + 未保护入口清单 + 每个建议的 schema 形状。
- 注:过严的格式约束(如强制 UUID)可能误伤合法输入,建议 schema 时按真实数据形状放宽。
与既有 skill 的边界
/omd-audit= 安全专项(信任边界/注入/认证/fail-open/越权)。- 通用正确性 / bug / contract 审查 →
/omd-review;确定性 semgrep 规则扫描(零 LLM,便宜)→/omd-sast,可先 sast 后 audit;某次失败的根因 →/omd-debug。 - 审出的高危项定型后 →
/omd-note记录或开 pathfinder 票map_add排修。
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 · 45 lines · 80 tokens per session scan A 6454df3c3707
omd-audit is a skill published in the GitHub repository AbyssCN/oh-my-dag (39 stars, last pushed yesterday), licensed MIT. It adds 80 tokens to every session and 963 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 2026-08-30.
Other skills, from other repositories
skill-test
Verifies that the skill system is working correctly.
interview-and-create-plan
Before starting a Ralph RLM loop, interview the user to sharpen the goal, stress-test the design, and write an authored PLAN.md (goal, definition of done, milestones, open questions, invariants) that the loop can follow. Use when a user wants to plan, scope, or stress-test work before delegating it to the supervisor /…
setup-opencode-ralph-rlm
Set up Ralph RLM in an existing OpenCode project by installing the package, running the opencode-ralph-rlm setup command, checking generated .opencode config, and verifying the provider/worker loop wiring. Use when a user asks to install, configure, initialize, troubleshoot setup for, or add opencode-ralph-rlm / Ralph…
clinicaltrials-database
Query ClinicalTrials.gov via API v2. Search trials by condition, drug, location, status, or phase. Retrieve trial details by NCT ID, export data, for clinical research and patient matching.
esm
Comprehensive toolkit for protein language models including ESM3 (generative multimodal protein design across sequence, structure, and function) and ESM C (efficient protein embeddings and representations). Use this skill when working with protein sequences, structures, or function prediction; designing novel…
pysam
Genomic file toolkit. Read/write SAM/BAM/CRAM alignments, VCF/BCF variants, FASTA/FASTQ sequences, extract regions, calculate coverage, for NGS data processing pipelines.