arsenal-tool-validation SKILL.md skillA

arsenal-tool-validation from miosa-osa/osa is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add miosa-osa/osa/arsenal-tool-validation@git:20260913.e13b6b8

Pins git:20260913.e13b6b8 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
miosa-osa/osa
Path
priv/skills/arsenal-tool-validation/SKILL.md
Versions recorded
1
Latest version
git:20260913.e13b6b8, committed Sep 13, 2026
Size
4,984 bytes
Repository stars
78
License
Apache-2.0

Tool-arsenal validation and risk gating for offensive engagements: risk-tier classification of tools (safe/active/intrusive/credential/dangerous), approval gates where intrusive tools are inert until approved (approve-once-then-free or pre-authorized allowlists), fail-safe denial for unattended runs, loud audited warnings for the hottest actions, egress scope enforcement, and pre-engagement availability checks. Use when preparing a toolset before an engagement, deciding which tools need…

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# Arsenal — Tool Validation & Risk Gating

Derived from T3MP3ST's `src/arsenal/` (Apache-2.0). The principle: **an
intrusive tool is INERT until a human has approved it** — and the hottest
actions fire a loud, audited warning every single time, even when approved.

## 1. Risk tiers

| Tier | Meaning | Gated? | Warning every use? |
|---|---|---|---|
| `safe` | read-only probes, passive recon | no | no |
| `active` | touches the target (scans, fuzzing) | no (scope-gated) | no |
| `intrusive` | exploits, state-changing actions | **yes** | no |
| `credential` | password attacks, credential stuffing | **yes** | **yes** |
| `dangerous` | full post-ex frameworks, destructive ops | **yes** | **yes** |

Undefined tier → treat as `safe` for gating but verify by inspection; a tool
that mutates state must never sit in `safe`.

## 2. The approval gate

Two ways a gated tool becomes approved:

1. **Interactive:** the first time the operator reaches for the tool, the system
   asks. A yes approves the TOOL (by name) for the rest of the session —
   "approve once, then free". Every use is still audited.
2. **Pre-authorized allowlist:** for headless/unattended runs (benchmarks,
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add miosa-osa/osa/arsenal-tool-validation@sha256:c4811b3da9af40ad

The line at the top of this page pins the label git:20260913.e13b6b8, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_pluqkf4tahqme54z.svg)](https://markdownregistry.com/a/art_pluqkf4tahqme54z)

3 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 1 version of this file, committed on Sep 13, 2026.

versioncommittedcommitsizeaudit
git:20260913.e13b6b8 latest2026-09-13 e13b6b8 4,984 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (4984 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

miosa-osa/osa · 78 stars · license Apache-2.0 · pushed 2026-10-29 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_pluqkf4tahqme54z
GET https://markdownregistry.com/api/v1/resolve?ref=miosa-osa/osa/arsenal-tool-validation
GET https://markdownregistry.com/api/v1/blob/c4811b3da9af40adc66800392b9821f8a15b6c2ab35b135e1afba20ee709f8f1

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from miosa-osa/osa

AGENTS.md@canopy/backend AGENTS.md file
miosa-osa/osa · canopy/backend/AGENTS.md
git:20260322.d94d08a · audit A · 78 stars
code-review SKILL.md skill
miosa-osa/osa · examples/skills/code-review/SKILL.md · Analyze pull requests and diffs for bugs, security vulnerabilities, performance issues, style violations, and test…
git:20260319.dccc501 · audit A · 78 stars
content-writer SKILL.md skill
miosa-osa/osa · examples/skills/content-writer/SKILL.md · Draft blog posts, social media content, email campaigns, and marketing copy
git:20260319.dccc501 · audit A · 78 stars
customer-support SKILL.md skill
miosa-osa/osa · examples/skills/customer-support/SKILL.md · Triage incoming support tickets, draft responses, detect customer sentiment, suggest knowledge base articles, and track…
git:20260319.dccc501 · audit A · 78 stars
daily-briefing SKILL.md skill
miosa-osa/osa · examples/skills/daily-briefing/SKILL.md · Generate a morning business briefing with weather, calendar, news, and task priorities
git:20260319.dccc501 · audit A · 78 stars
email-assistant SKILL.md skill
miosa-osa/osa · examples/skills/email-assistant/SKILL.md · Triage inbox, flag urgent emails, summarize threads, and draft replies
git:20260319.dccc501 · audit A · 78 stars
meeting-prep SKILL.md skill
miosa-osa/osa · examples/skills/meeting-prep/SKILL.md · Research attendees, prepare talking points, and summarize previous interactions before meetings
git:20260319.dccc501 · audit A · 78 stars
research-assistant SKILL.md skill
miosa-osa/osa · examples/skills/research-assistant/SKILL.md · Conduct deep, multi-source research on technologies, companies, markets, and topics — synthesizing findings into…
git:20260319.dccc501 · audit A · 78 stars
sales-pipeline SKILL.md skill
miosa-osa/osa · examples/skills/sales-pipeline/SKILL.md · Monitor sales pipeline, track deals, send follow-up reminders, and forecast revenue
git:20260319.dccc501 · audit A · 78 stars
attack-simulation SKILL.md skill
miosa-osa/osa · priv/skills/attack-simulation/SKILL.md · Run cyber defense attack simulations against isolated lab targets, compare detection gaps, apply a lab patch and rerun…
v1.0.200 · audit A · 78 stars
code-review SKILL.md skill
miosa-osa/osa · priv/skills/code-review/SKILL.md · Analyze pull requests and diffs for bugs, security vulnerabilities, performance issues, style violations, and test…
git:20260430.84eced6 · audit A · 78 stars
content-writer SKILL.md skill
miosa-osa/osa · priv/skills/content-writer/SKILL.md · Draft blog posts, social media content, email campaigns, and marketing copy
git:20260430.84eced6 · audit A · 78 stars

Every file in miosa-osa/osa

Browse by kind, by grade A, or by owner.