ai-security SKILL.md skillA
ai-security from arcasilesgroup/ai-engineering is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add arcasilesgroup/ai-engineering/ai-security@git:20261004.3e3bd00Pins git:20261004.3e3bd00 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- arcasilesgroup/ai-engineering
- Path
skills/ai-security/SKILL.md- Versions recorded
- 7
- Latest version
- git:20261004.3e3bd00, committed Oct 4, 2026
- First version recorded
- Sep 1, 2026
- Size
- 14,435 bytes
- Repository stars
- 62
- License
- Apache-2.0
Six-phase security audit of a codebase — web apps, APIs, services, CLI tools, libraries, and daemons — with adversarial validation: the agent that verifies a finding is never the one that found it. Recon, parallel hunting across 8 attack classes, validation, reporting, schema-validated findings.json, and independent verification. Only exploitable issues with real impact are reported — never theoretical concerns or industry-standard behavior. Use when a milestone declares a security audit, when…
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
# ai-security — six-phase security audit with adversarial validation You are a security auditor. Your job is to find **exploitable vulnerabilities with real impact**. ## Platform terminology This skill is agent-neutral. In the methodology: - **Task tool** means the coding agent's delegation or sub-agent mechanism. - **`research` agent** means a delegated agent optimized for focused codebase exploration and factual verification. - **`general` agent** means a delegated agent that can investigate broadly and spawn focused research agents. - **`subagent_type`** means the equivalent delegated-agent role supported by the current platform. Use the platform's equivalent capabilities while preserving the specified roles, parallelism, prompts, and independence boundaries. ## Setup Before starting, establish two paths: - **Target**: the codebase to audit (from the user's request or the current working directory) …
Read the whole file at its exact version.
How to install
mdr add arcasilesgroup/ai-engineering/ai-security@sha256:56dfe2a6feb43e64The line at the top of this page pins the label git:20261004.3e3bd00, 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.
[](https://markdownregistry.com/a/art_hrglpdvb25xcdepc)
4 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 7 versions of this file, between Sep 1, 2026 and Oct 4, 2026, about one every 6 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261004.3e3bd00 latest | 2026-10-04 | 3e3bd00 | 14,435 B | A | view · diff |
| git:20260926.b0fd9cf | 2026-09-26 | b0fd9cf | 14,241 B | A | view · diff |
| git:20260923.5be86d2 | 2026-09-23 | 5be86d2 | 14,327 B | A | view · diff |
| git:20260916.a045fa9 | 2026-09-16 | a045fa9 | 13,314 B | A | view · diff |
| git:20260910.d021330 | 2026-09-10 | d021330 | 12,859 B | A | view · diff |
| git:20260901.deb68d3 | 2026-09-01 | deb68d3 | 12,322 B | A | view · diff |
| git:20260901.dca22e5 | 2026-09-01 | dca22e5 | 2,137 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (14435 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
arcasilesgroup/ai-engineering · 62 stars · license Apache-2.0 · pushed 2026-10-19 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_hrglpdvb25xcdepc GET https://markdownregistry.com/api/v1/resolve?ref=arcasilesgroup/ai-engineering/ai-security GET https://markdownregistry.com/api/v1/blob/56dfe2a6feb43e640b6007f43d751bc64ba37f7be32b012e4c9752134f0ffe0a
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 arcasilesgroup/ai-engineering
Every file in arcasilesgroup/ai-engineering