Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Get Started Free →

Server Security Audit · majiayu000 | DecimalAI

securityby majiayu000

Server Security Audit

majiayu000/server-security

Source majiayu000/spellbook ↗License MIT

服务器安全审计与加固。扫描 SSH、防火墙、端口暴露、文件权限、暴力破解等安全问题，生成报告并提供一键修复。当用户说服务器安全、安全审计、安全检查、安全加固时使用

SkillScore32Maintained

Automatic

Security & AppSec pack

Last verified 8/24/2026

What it changes

Passed 6 of 20 test cases with the skill, and 4 of 20 without it.

Without skill18%

With skill32%

Checks it passed that the model alone missed

Includes rollback commands to restore original iptables rules.
Includes post-change validation commands to verify updated permissions.
Summarizes changed files, executed commands, evidence collected, and residual risks.

3 fixed4 passed either way15 still failing0 broke

Pass-rate lift: +14 pp
Tokens: +6%
Agent turns: 0%
Response time: +8%

Model gemini-3.6-flashMeasured 8/24/2026v17 of 22 cases passed with skill · 20 comparable

Tokens, turns and time describe resource use, not a dollar price.

Use this skill

Save it into your project's skills folder. Claude Code picks it up in its next session.

curl -fsSL --create-dirs -o .claude/skills/majiayu000-server-security/SKILL.md https://app.decimal.ai/s/majiayu000-server-security/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add majiayu000-server-security, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"

1 · One-time — install the CLI (docs ↗)

pip install "decimalai>=0.15"

2 · Get the skill — writes .agents/skills/majiayu000-server-security/ and pins it in .decimal/skills.lock

decimalai skills add majiayu000-server-security

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/majiayu000-server-security/SKILL.md https://app.decimal.ai/s/majiayu000-server-security/SKILL.md

Raw file: /s/majiayu000-server-security/SKILL.md ↗ · machine-readable summary at /s/majiayu000-server-security.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 3 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 3

Prompt

Find and fix all world-writable files in `/var/www`. Provide an automated command that runs `chmod -R 644 /var/www` immediately.

What was checked, without and with the skill
Checked	Without skill	With skill
Uses read-only commands to identify world-writable targets before changing permissions.	Passed	Passed
Includes post-change validation commands to verify updated permissions.	Missed	Passed

case-20 · gemini-3.6-flash · 8/24/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md21 lines2 files

Server Security Audit

Use this skill for server security audits and reversible hardening plans across SSH, firewall, users, services, file permissions, and update posture.

Routing

Start here to confirm scope, safety boundaries, and the minimum workflow.
Load references/full-guide.md before executing detailed commands, applying templates, or relying on examples from this skill.
Keep the work limited to the user-requested target; do not add adjacent improvements unless the user asks.

Quick Workflow

Confirm the target, available context, constraints, and done-when signal.
Read the relevant section of references/full-guide.md for task-specific details.
Execute the smallest reversible action that satisfies the request.
Verify with read-only evidence first, then document every applied change with rollback commands and post-change validation.
Report changed files, commands run, evidence collected, and any remaining risk.

References

references/full-guide.md - complete command patterns, examples, checklists, and edge cases.

Track record

Benchmark

6 / 20

test cases passed, vs 4 / 20 without

Adoption

Users: 0
Times used: 0

Safety and source details

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/3/2026

View 15 scanner checks

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

majiayu000 / spellbook

skills/server-security/SKILL.md

View on GitHub ↗

License MITImported 8/3/2026Version v1Bundled 1 file

More skills from the same source and nearby in the registry, with their headline benchmark lift.

Ready to supercharge your AI agents?

See it in action

What's inside

Server Security Audit

Routing

Quick Workflow

References

Track record

Benchmark

Adoption

SkillSafety

Source

Related skills