Home / int2t05 / engineering-skills · GitHub

security-review SKILL.md skillA

security-review from int2t05/engineering-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned

mdr add int2t05/engineering-skills/security-review@git:20261015.f440cbb

Pins git:20261015.f440cbb in mdr.lock. Pin the fingerprint instead.

Audit grade: A, 17 of 17 checks passed
Kind: SKILL.md skill
Repository: int2t05/engineering-skills
Path: skills/07-verify/security-review/SKILL.md
Versions recorded: 5
Latest version: git:20261015.f440cbb, committed Oct 15, 2026
First version recorded: Aug 12, 2026
Size: 1,798 bytes
Repository stars: 3
License: MIT

Audit actual trust boundaries and abuse paths with current guidance. Triggers on "security review", "安全审查".

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

# Security Review

## When to use

- Audit actual trust boundaries and abuse paths with current guidance.

**Not for:** auth-implementation for building auth; incident-response for compromise.

## Steps

1. Identify assets, inputs, identities and relevant changes; verify authoritative current references.

2. Trace injection, cross-user access, upload, secret and supply-chain abuse paths.

3. For LLM features, inspect enforced tool permissions, untrusted input and output handling rather than relying on prompt instructions.

4. Validate safe reproduction and report impact, severity and remedies at the approved path; retest fixes and state assessment limits.

**Output:** Suggested paths, subject to [human audit](../../../references/human-audit.md): `docs/security-report.md` when durable findings are requested.

## Verify

- Findings tie attacker-controlled inputs to actual impact; checklist completion is not proof of security.

## References

- [engineering-principles.md](../../../references/engineering-principles.md) — shared decision boundaries, scope and verification.
- [human-audit.md](../../../references/human-audit.md) — document consent, readability and human review.
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint

mdr add int2t05/engineering-skills/security-review@sha256:e31f8c6ba8670a59

The line at the top of this page pins the label git:20261015.f440cbb, 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](https://markdownregistry.com/badge/art_4ra4ds2hsfniazke.svg)](https://markdownregistry.com/a/art_4ra4ds2hsfniazke)

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

Versions

The registry has recorded 5 versions of this file, between Aug 12, 2026 and Oct 15, 2026, about one every 16 days.

version	committed	commit	size	audit
git:20261015.f440cbb latest	2026-10-15	f440cbb	1,798 B	A	view · diff
git:20261008.a85674e	2026-10-08	a85674e	11,784 B	A	view · diff
git:20260814.e4441f3	2026-08-14	e4441f3	11,383 B	A	view · diff
git:20260813.a99b100	2026-08-13	a99b100	10,198 B	A	view · diff
git:20260812.4d783a6	2026-08-12	4d783a6	10,141 B	A	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 (1798 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

int2t05/engineering-skills · 3 stars · license MIT · pushed 2026-10-15 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_4ra4ds2hsfniazke
GET https://markdownregistry.com/api/v1/resolve?ref=int2t05/engineering-skills/security-review
GET https://markdownregistry.com/api/v1/blob/e31f8c6ba8670a591c7be0019bb56dce36b05d7f12308c986f68dc3a3abf9f79

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.