security-reviewer SKILL.md skillA
security-reviewer from ralvarez-ai/ralvaskills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add ralvarez-ai/ralvaskills/security-reviewer@v1.1.0Pins v1.1.0 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- ralvarez-ai/ralvaskills
- Path
skills/quality/security-reviewer/SKILL.md- Versions recorded
- 5
- Latest version
- v1.0.0, committed Nov 6, 2026
- First version recorded
- May 21, 2026
- Size
- 8,566 bytes
- Repository stars
- 4
- License
- GPL-3.0
Cross-language security review — injection, auth/authz, secrets, insecure defaults, deserialization, CSRF/SSRF/IDOR, dep vulns. Emits a Critical/High/Medium/Low report with file:line + fixes. Use when auditing a PR or pre-release.
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 Reviewer Reviews code for security issues before they reach production. This skill catches the issues that architect skills already encode rules against; it's the safety net. Findings table, severity rubric, and tooling reference in [RECIPES.md](RECIPES.md). ## 1. When to invoke - User asks "review this for security", "audit", "is this safe", "any security issues". - Pre-release review of a service touching auth, payments, PII, or external integration. - After dependency updates that include security advisories. - New endpoint, new auth flow, new SQL query — anything where the failure mode is "data leaks" or "user gets owned". ## 2. Output format Structured findings report — one row per finding with severity, rule, location, evidence, and fix. Layout + severity rubric + closing summary in [RECIPES § 1–2](RECIPES.md#1-findings-report-format). ## 3. Review approach Two passes: 1. **Tool pass** — run static analyzers, then read their output. They catch low-hanging fruit fast. 2. **Read pass** — read the actual diff (or files in scope), checking the categories in §4. Tools miss intent; the read pass finds most real issues. ## 4. What to check — by category …
Read the whole file at its exact version.
How to install
mdr add ralvarez-ai/ralvaskills/security-reviewer@sha256:b46a48ed7e135e49The line at the top of this page pins the label v1.1.0, 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.
[](https://markdownregistry.com/a/art_riqlreu5zmfknbz4)
1 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 5 versions of this file, between May 21, 2026 and Nov 6, 2026, about one every 42 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| v1.0.0 latest | 2026-11-06 | 6bc3c77 | 8,566 B | A | view · diff |
| v1.1.0 | 2026-11-06 | f1dba2a | 8,566 B | A | view · diff |
| v1.0.0 | 2026-05-22 | f678526 | 8,767 B | A | view · diff |
| v1.0.0 | 2026-05-22 | e1b4216 | 8,765 B | A | view · diff |
| v1.0.0 | 2026-05-21 | 1548524 | 11,156 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 (8566 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
ralvarez-ai/ralvaskills · 4 stars · license GPL-3.0 · pushed 2026-11-06 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_riqlreu5zmfknbz4 GET https://markdownregistry.com/api/v1/resolve?ref=ralvarez-ai/ralvaskills/security-reviewer GET https://markdownregistry.com/api/v1/blob/b46a48ed7e135e49d179c497242ca0caccd4f3e82b8f43be7b3ae34316f7e480
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 ralvarez-ai/ralvaskills
Every file in ralvarez-ai/ralvaskills