Home / Skills / agent-security-hardening

agent-security-hardening

Security hardening guidance for AI agent frameworks that process untrusted content, invoke tools, write workspace files, manage runtime identifiers, or handle credentials. Use when building or reviewing an agent runtime, autonomous worker, tool gateway, memory service, or multi-tenant agent deployment. Do not use for general web application security or offensive testing.

ScannedSkillSource: GitHub

284,120 stars Updated 16d ago License MIT Context ≈100 tokens always loaded

96popular

Why this score

Stars

31/35

Usage (forks)

15/15

Upkeep

25/25

License

15/15

Owner history

10/10

This repo hosts 10 skills, so its 284,120 stars are split between them (about 28,412 each) for scoring.

Popularity score: 96/100 from public GitHub signals only. It shows how widely used and maintained this is, not how well it works. Not included yet: the fake-star check. The security scan is shown separately and doesn't change the score. How we rank

Security

Scanned Oct 20, 2026 at commit 5af4395e5c52, with Cisco's open-source skill-scanner.

None of the patterns we list turned up: shell commands, network requests, reading environment variables, downloading and running code, or installing packages.

A scan lists patterns in the code. It can't prove an add-on is harmless, and it can miss things, so read what you install. How we scan

Alternatives

Other makers' add-ons that do the same job, next to this one.

Name	Score	Stars	Context	Updated
This oneagent-security-hardening affaan-m/ECC · Skill	96	★ 284k	≈100 always	16d ago
propose-security-hardening openai/codex-security · Skill Both about hardening and security	80	★ 11k	≈156 always	16d ago
agent-security UnitOneAI/SecuritySkills · Skill Both about security	52	★ 87	≈23 always	5mo ago
09-web-security Masriyan/Claude-Code-CyberSecurity-Skill · Skill Both about security and testing	66	★ 490	≈21 always	19d ago
roblox-security TabooHarmony/roblox-brain · Skill Both about hardening and security	59	★ 114	≈34 always	20d ago
owasp-security agamm/claude-code-owasp · Skill Both about hardening and security	70	★ 386	≈118 always	1mo ago

Install

mkdir -p .claude/skills/agent-security-hardening

curl -sL https://codeload.github.com/affaan-m/ECC/tar.gz/5af4395e5c52643b7f5ecc716079cd253504b354 | tar -xz -C .claude/skills/agent-security-hardening --strip-components=3 "ECC-5af4395e5c52643b7f5ecc716079cd253504b354/skills/agent-security-hardening"

To remove it later:

rm -rf .claude/skills/agent-security-hardening

npx skills add affaan-m/ECC --skill agent-security-hardening

Pinned to commit 5af4395e5c52 as listed by GitHub.

Context cost: ≈100 tokens loaded every session (name and description), plus ≈2.7k tokens when the skill is used.

The Claude Code command downloads this skill folder at the pinned commit into .claude/skills/. The Skills CLI (npx skills) works with many agents but can't pin a version, so it installs whatever is current.

Used for

Engineering › Testing & QA Engineering › DevOps & cloud Security › Security review

Facts

Repo: affaan-m/ECC
Stars: 284,120
Forks: 42,206
Last push: 2026-10-19 (16d ago)
License: MIT
Owner: affaan-m · since 2023
Language: JavaScript
Works with: Claude Code, Skills CLI