菜单
MCP threat-model artifact for a scaffolded harness. Reports allowed/denied tools, dangerous permissions count, secrets reachability, network/shell/file-write grants, default-deny posture. Verdict: clean (exit 0) / medium (exit 1) / high (exit 2). The 'enterprise gold' artifact for PR + compliance review.
默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。
决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/ruvnet/metaharness --skill threat-model命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
正在显示 SKILL.md
Evolve this harness with Darwin Mode — frozen model, evolving harness (real, sandboxed, safety-gated).
Diff two scaffolded harnesses (ADR-031). Reports manifest meta drift + host list + per-file fingerprint changes (added/removed/changed). Exits 0 IDENTICAL, 1 DRIFT, 2 missing manifest. Use --bundle for the ADR-031 schema-1 JSON envelope.
Kernel-version skew check (ADR-027). Reports manifest surface + manifest kernel + installed kernel + verdict (match/patch-diff/minor-diff/major-diff). Exits 1 on minor/major skew with a copy-pasteable `npm install @metaharness/kernel@X.Y.Z` next step. Exits 2 if no .harness/manifest.json at path.
基于 SOC 职业分类
| name | threat-model |
| description | MCP threat-model artifact for a scaffolded harness. Reports allowed/denied tools, dangerous permissions count, secrets reachability, network/shell/file-write grants, default-deny posture. Verdict: clean (exit 0) / medium (exit 1) / high (exit 2). The 'enterprise gold' artifact for PR + compliance review. |
Codex skill: MCP threat-model artifact for PR / compliance review (iter 112 → iter 114). User-labelled "enterprise gold."
Renders the existing mcp-scan findings as a clean threat-model artifact
in the shape a security / compliance reviewer wants to see attached to a
PR:
MCP Threat Model
Allowed tools: 3
Denied tools: 14
Dangerous permissions: 0
Secrets reachable: no
Network access: no
Shell access: no
File write: no
Default-deny policy: yes
Audit log: yes
Verdict: clean (exit 0)
Same underlying scan as mcp-scan, presented as a single-screen artifact.
| Verdict | Exit | Triggers |
|---|---|---|
clean | 0 | no dangerous perms, no secret exposure |
medium | 1 | network OR file-write granted, OR no audit log |
high | 2 | shell granted OR default-deny OFF OR secrets reachable |
The "secrets reachable" heuristic is conservative: true when MCP is in
use AND deny rules don't guard .env* AND allow rules include any
Read(...) grant.
/threat-model path=./my-harness
/threat-model path=./my-harness bundle=true
harness threat-model ./my-harness # text artifact
harness threat-model ./my-harness --json # full envelope
harness threat-model ./my-harness --bundle # ADR-031 schema-1
harness threat-model ./my-harness --out tm.json # write to file
.harness/mcp-policy.json or .claude/settings.json
permissionsThe artifact is small enough to paste verbatim into the PR description.
validate-harness (iter 22) — release-readiness umbrella (includes
mcp-scan)score-harness (iter 114) — broader 0-100 scorecard; MCP safety is
one of its 5 dimensionsrepo-genome (iter 114) — pre-scaffold readiness; MCP risk is one of
its 7 sections