Magnus Security Review

Perform a requested, project-specific security review of a codebase, diff, PR, module, or repository. Use for an explicit security audit; ordinary security-adjacent edits do not activate it.

5 starsSecurity

Install

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add Magnus-Gille/claude-skills --skill magnus-security-review
Manual install
git clone --depth 1 https://github.com/Magnus-Gille/claude-skills.git /tmp/claude-skills
mkdir -p ~/.claude/skills
cp -r /tmp/claude-skills/codex/magnus-security-review ~/.claude/skills/magnus-security-review

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# Magnus Security Review

Run the requested review in three phases: threat model, targeted analysis, and validation/remediation. Keep findings grounded in reachable data flow and state residual uncertainty instead of manufacturing issues.

## Scope and workflow

1. State the repository and exact scope. Review one repository at a time.
2. Read the relevant code, tests, configuration, architecture, and deployment context before scanning. For a full-repository or comprehensive review, read [references/checklists.md](references/checklists.md) and select the categories that apply; for a small diff, inspect only relevant categories.
3. Map entry points, exits, assets, trust boundaries, and privileged operations. Summarize the likely STRIDE risks.
4. Trace inputs to security-sensitive sinks and inspect classic web/API, dependency, infrastructure, CI, IAM, native-safety, and LLM risks that the scope can reach.
5. Validate each candidate against reachability, guards, framework defaults, tests, and exploitability. Mark it Confirmed, Likely, or Theoretical and rate severity by impact and exploitability.
6. Self-critique findings, remove noise, and propose a concrete fix. Do not claim a scanner result, deployment state, or mitigation that was not observed.

For a full review, also inspect relevant security history and sibling occurrences of past fixes. Keep temporary review artifacts out of the repository unless the user requests a durable threat model.

## Output
Read the full skill on GitHub

Details

Skill name
magnus-security-review
Path
codex/magnus-security-review/SKILL.md
License
MIT
Repo updated
16 November 2026

FAQ

What does the Magnus Security Review skill do?

Perform a requested, project-specific security review of a codebase, diff, PR, module, or repository. Use for an explicit security audit; ordinary security-adjacent edits do not activate it.

How do I install the Magnus Security Review skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add Magnus-Gille/claude-skills --skill magnus-security-review. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Magnus Security Review popular?

It lives in Magnus-Gille/claude-skills, which has 5 GitHub stars and 0 forks.

Related skills

Close

5

Magnus-Gille/claude-skills

Close a coding-agent session or produce its final handoff only when the user explicitly asks to close, wrap up, or produce an end-of-session handoff.

AI, LLMs & Agents

Cloudflare Private Static Site

5

Magnus-Gille/claude-skills

Create, preview, test, release, verify, or roll back a small static Cloudflare site protected by per-person HTTP Basic Auth. Use for private briefings, reports, one-pagers, document portals, or similar sites that should go from finished content to a custom domain in about ten minutes. Do not use for full applications or when the user requires SSO, identity lifecycle, or Cloudflare Access policy management.

DevOps & Cloud

Code Friction

5

Magnus-Gille/claude-skills

Capture a small, opt-in set of concrete code-changeability observations during a coding task and hand them to Close without affecting readiness.

Software Development

Godmode

9

Lord1Egypt/RA-Skills

Jailbreak LLMs: Parseltongue, GODMODE, ULTRAPLINIAN.

Security

Bio Entrez Search

9

hackernoon/cuttlefish-agent-skills

Search NCBI databases using Biopython Bio.Entrez (ESearch, EInfo, EGQuery, ESpell). Use when finding records by keyword, building reproducible field-qualified queries, navigating the Entrez Query Translator, exploiting the history server for large result sets, handling retmax caps, or interpreting weekly index lag. Covers PubMed, Nucleotide, Protein, Gene, SRA, GEO, Assembly, Taxonomy, ClinVar, dbSNP.

Security

Dependency Safety Check

5

bolasblack/claude-skills

Screens third-party project dependencies for known vulnerabilities and supply-chain risk before installation using a bundled check-deps.py script. Use when user asks to install, add, update, upgrade, or pin packages with npm, pnpm, yarn, bun, pip, uv, poetry, or cargo, or when deciding whether a package version is safe to install. Do NOT use for OS package managers such as apt, brew, yum, apk, or pacman.

Security

Browse the most popular Claude skills, all security skills, or write your own with the skills generator.