AGENTS.md@agents/security-reviewA

AGENTS.md@agents/security-review from gsa-tts/agentic-coding-patterns is an AGENTS.md file: the standing instructions coding agents read in that repo.

Install it, pinned
mdr add gsa-tts/agentic-coding-patterns/agents/security-review/AGENTS.md@v1.0.0

Pins v1.0.0 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 14 of 14 checks passed
Kind
AGENTS.md file
Repository
gsa-tts/agentic-coding-patterns
Path
agents/security-review/AGENTS.md
Versions recorded
5
Latest version
v1.0.0, committed Jul 28, 2026
First version recorded
May 20, 2026
Size
6,937 bytes
Repository stars
16
License
CC0-1.0

Security-focused agent instructions for vulnerability identification and responsible disclosure.

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 Agent Instructions

Security-focused agent instructions for vulnerability identification and secure code review.

> For complete behavioral rules, see [main AGENTS.md](../../AGENTS.md)

## Core Principles

```
safety > responsible disclosure > accuracy > completeness
```

1. **Safety** — Never create exploit code or weaponized payloads
2. **Responsible Disclosure** — Report vulnerabilities privately
3. **Accuracy** — Minimize false positives
4. **Completeness** — Cover all OWASP Top 10

## Review Process

### 1. Threat Modeling

**Identify:**

- Attack surface (inputs, APIs, endpoints)
- Trust boundaries (client/server, user roles)
- Data flows (where sensitive data goes)
- Authentication/authorization points

**Ask:**

- What could an attacker control?
- What are the valuable targets?
- What are the consequences of compromise?

### 2. OWASP Top 10 Checklist

**A01: Broken Access Control**

- [ ] Authorization checked server-side
- [ ] Least privilege enforced
- [ ] No client-side-only checks

**A02: Cryptographic Failures**

- [ ] Sensitive data encrypted at rest
- [ ] TLS 1.2+ for transit
- [ ] No hardcoded keys
- [ ] Strong algorithms only

**A03: Injection**
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add gsa-tts/agentic-coding-patterns/agents/security-review/AGENTS.md@sha256:643e993bb77b1ec7

The line at the top of this page pins the label v1.0.0, 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_sjhk4y5g6ayybczq.svg)](https://markdownregistry.com/a/art_sjhk4y5g6ayybczq)

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

Versions

The registry has recorded 5 versions of this file, between May 20, 2026 and Jul 28, 2026, about one every 17 days.

versioncommittedcommitsizeaudit
v1.0.0 latest2026-07-28 ea6ea67 6,937 BA view · diff
v1.0.02026-06-29 a2aa1ac 6,692 BA view · diff
v1.0.02026-06-22 c69b6a0 6,524 BA view · diff
v1.0.02026-05-26 a36cc8a 6,506 BA view · diff
v1.0.02026-05-20 763c423 6,483 BA view

Audit of the latest version

A  14 of 14 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Size between 200 bytes and 200 KB (6937 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

gsa-tts/agentic-coding-patterns · 16 stars · license CC0-1.0 · pushed 2026-10-19 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_sjhk4y5g6ayybczq
GET https://markdownregistry.com/api/v1/resolve?ref=gsa-tts/agentic-coding-patterns/agents/security-review/AGENTS.md
GET https://markdownregistry.com/api/v1/blob/643e993bb77b1ec786610cf9948ed8796f93e4ef167fbc67a70f2aef7e6a5ec4

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: how to write a good AGENTS.md · AGENTS.md vs CLAUDE.md · which agent file does what.

More from gsa-tts/agentic-coding-patterns

agentic-actions-auditor SKILL.md skill
gsa-tts/agentic-coding-patterns · .agents/skills/agentic-actions-auditor/SKILL.md · Audit CI/CD workflows that invoke LLM agents for dangerous trigger, checkout, token-scope, and prompt-construction…
v1.0.0 · audit A · 16 stars
backdoor-review SKILL.md skill
gsa-tts/agentic-coding-patterns · .agents/skills/backdoor-review/SKILL.md · Read-only adversarial review that flags suspicious-pattern classes (auth bypass, unauthorized persistence, CI…
v1.0.0 · audit A · 16 stars
agentic-value-analyst SKILL.md skill
gsa-tts/agentic-coding-patterns · .agents/skills/communications/agentic-value-analyst/SKILL.md · Translate agentic-coding capabilities into organizational value without hype — labeling every claim by evidence class…
v0.1.0 · audit A · 16 stars
artifact-brief SKILL.md skill
gsa-tts/agentic-coding-patterns · .agents/skills/communications/artifact-brief/SKILL.md · Capture the audience, action, core message, evidence, and constraints for a communication artifact before any design or…
v1.0.0 · audit B · 16 stars
artifact-qa SKILL.md skill
gsa-tts/agentic-coding-patterns · .agents/skills/communications/artifact-qa/SKILL.md · Render, inspect, and validate a produced communication artifact against its brief and visual contract — checking the…
v1.0.0 · audit B · 16 stars
narrative-architect SKILL.md skill
gsa-tts/agentic-coding-patterns · .agents/skills/communications/narrative-architect/SKILL.md · Turn an artifact brief into an information hierarchy and argument sequence — the order in which points are made and how…
v1.0.0 · audit B · 16 stars
one-pager SKILL.md skill
gsa-tts/agentic-coding-patterns · .agents/skills/communications/one-pager/SKILL.md · Render a single-page executive artifact (HTML source plus PDF/PNG exports) from a storyboard and visual contract…
v1.0.0 · audit B · 16 stars
slide-deck SKILL.md skill
gsa-tts/agentic-coding-patterns · .agents/skills/communications/slide-deck/SKILL.md · Render a presentation deck (HTML source plus PDF export and a PNG preview) from a storyboard and visual contract, one…
v1.0.0 · audit B · 16 stars
software-delivery-explainer SKILL.md skill
gsa-tts/agentic-coding-patterns · .agents/skills/communications/software-delivery-explainer/SKILL.md · Explain how software moves from a need to production, and exactly where AI agents participate and where the human…
v0.1.0 · audit A · 16 stars
technical-concept-translator SKILL.md skill
gsa-tts/agentic-coding-patterns · .agents/skills/communications/technical-concept-translator/SKILL.md · Translate one software-engineering, security, or agentic-system concept into an accurate executive mental model — what…
v0.1.0 · audit A · 16 stars
visual-direction SKILL.md skill
gsa-tts/agentic-coding-patterns · .agents/skills/communications/visual-direction/SKILL.md · Turn a storyboard into a concrete visual contract — layout, type scale, color, spacing, and asset rules (USWDS-aligned…
v1.0.0 · audit B · 16 stars
compliance-claim-checker SKILL.md skill
gsa-tts/agentic-coding-patterns · .agents/skills/compliance-claim-checker/SKILL.md · Review documentation and PRs for federal compliance claims (FedRAMP, NIST, OWASP, Section 508) and flag uncited or…
v1.0.0 · audit A · 16 stars

Every file in gsa-tts/agentic-coding-patterns

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