security
Reviews code, a diff, or a repository for exploitable security flaws by tracing attacker-controlled input to dangerous sinks, then reports verified findings…
Skill by nanstey
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/nanstey-security
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: security
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/security
What's inside
- Skill name
security- Description
- Reviews code, a diff, or a repository for exploitable security flaws by tracing attacker-controlled input to dangerous sinks, then reports verified findings with severity, confidence, and suggested fixes. Use when asked to security-review, audit, or check code for vulnerabilities, secrets, unsafe dependencies, or weak auth, or after changes to auth, input handling, secrets, or trust boundaries.
- License
- unknown
- Instructions
- 69 lines in SKILL.md · view on GitHub
Files (5)
- SKILL.md
- checks.md · references/
- jev.md · references/
- questions.json · references/
- report.md · references/
The license isn't open source, so the instructions aren't shown here. Read SKILL.md on GitHub
More from nanstey/agentic-tools
- 0.598score
pr
nanstey
Runs PR creation, maintenance, and stacked-PR workflows from one command.
SkillAFreshness: A★ 2Claude Code +9 - 0.598score
bugs
nanstey
Hunts functional defects in code, a diff, or a repository by tracing real execution paths, challenging each suspect, and reporting only bugs with a concrete…
SkillAFreshness: A★ 2Claude Code +9 - 0.598score
complexity
nanstey
Measures cyclomatic complexity, function length, and parameter count on code with Lizard, then judges whether code needs refactoring.
SkillAFreshness: A★ 2Claude Code +9 - 0.598score
refactor
nanstey
Reviews and fixes code smells, design principles, maintainability, over-engineering.
SkillAFreshness: A★ 2Claude Code +9 - 0.598score
risk-review
nanstey
Produces an evidence-led, read-only change review with impact paths, required checks, and verified findings.
SkillAFreshness: A★ 2Claude Code +9 - 0.598score
git
nanstey
Runs everyday git workflows from one command — branching, worktrees, change review, commits, rebasing, and conflict resolution.
SkillAFreshness: A★ 2Claude Code +9 - 0.593score
new-app
nanstey
Scaffolds a new local software project from scratch — folder structure, git, README, LICENSE, .gitignore, optional CI, and a first commit — delegating…
SkillAFreshness: A★ 2Claude Code +9 - 0.593score
make-skill
nanstey
Creates new repo-native skills from plan to scaffolded `SKILL.md` and catalog entry.
SkillAFreshness: A★ 2Claude Code +9 - 0.593score
make-agent
nanstey
Creates new repo-native agent profiles from plan to scaffolded `agents/<name>.md` and catalog alignment.
SkillAFreshness: A★ 2Claude Code +9 - 0.593score
handoff
nanstey
Hands a task off to a new standalone Pi session in a fresh Orca worktree that drives it to review-ready PRs with idea-to-pr, then stops work on it.
SkillAFreshness: A★ 2Claude Code +9 - 0.593score
reflect
nanstey
Reviews the current session for problems and their eventual fixes, then proposes durable improvements to repo skills, scripts, or docs that prevent recurrence.
SkillAFreshness: A★ 2Claude Code +9 - 0.593score
scope
nanstey
Confirms and normalizes analysis scope, then returns clear scope assumptions.
SkillAFreshness: A★ 2Claude Code +9
Signals
- Stars
- 2
- Forks
- 2
- Open issues
- 0
- Last commit (this folder)
- Oct 20, 2026 (9 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- License unknown
- Repository
- github.com/nanstey/agentic-tools
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from nanstey
- 0.598score
refactor
nanstey
Reviews and fixes code smells, design principles, maintainability, over-engineering.
SkillAFreshness: A★ 2Claude Code +9 - 0.598score
git
nanstey
Runs everyday git workflows from one command — branching, worktrees, change review, commits, rebasing, and conflict resolution.
SkillAFreshness: A★ 2Claude Code +9 - 0.598score
bugs
nanstey
Hunts functional defects in code, a diff, or a repository by tracing real execution paths, challenging each suspect, and reporting only bugs with a concrete…
SkillAFreshness: A★ 2Claude Code +9 - 0.598score
complexity
nanstey
Measures cyclomatic complexity, function length, and parameter count on code with Lizard, then judges whether code needs refactoring.
SkillAFreshness: A★ 2Claude Code +9 - 0.598score
risk-review
nanstey
Produces an evidence-led, read-only change review with impact paths, required checks, and verified findings.
SkillAFreshness: A★ 2Claude Code +9 - 0.598score
pr
nanstey
Runs PR creation, maintenance, and stacked-PR workflows from one command.
SkillAFreshness: A★ 2Claude Code +9
Cite this page
security skill. Agent Mart. https://agentmart.dev/skills/nanstey-security (last updated 2026-10-24)