Ready to supercharge your AI agents?

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

Get Started Free →

☣️ Malware Analyst & Link Safety Master · dokhacgiakhoa | DecimalAI

securityby dokhacgiakhoa

☣️ Malware Analyst & Link Safety Master

dokhacgiakhoa/malware-analyst

Source dokhacgiakhoa/agent-skills-4-vibe-coding-cli ↗License NOASSERTION

MASTER MALWARE ANALYSIS: Threat Intelligence, Phishing Detection.

SkillScore68Maintained

Automatic

Security & AppSec pack

Last verified 8/29/2026

What it changes

Passed 15 of 22 test cases with the skill, and 6 of 22 without it.

Without skill27%

With skill68%

Checks it passed that the model alone missed

Requires expanding shortened URLs prior to validation.
Ranks the threat level as Clean, Suspicious, or Malicious.
Assigns a threat level using Clean, Suspicious, or Malicious.

and 10 more in the full report

9 fixed6 passed either way7 still failing0 broke

Pass-rate lift: +41 pp
Tokens: -8%
Agent turns: 0%
Response time: -20%

Model gemini-3.6-flashMeasured 8/29/2026v115 of 22 cases passed with skill

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/dokhacgiakhoa-malware-analyst/SKILL.md https://app.decimal.ai/s/dokhacgiakhoa-malware-analyst/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add dokhacgiakhoa-malware-analyst, 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/dokhacgiakhoa-malware-analyst/ and pins it in .decimal/skills.lock

decimalai skills add dokhacgiakhoa-malware-analyst

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

curl -fsSL --create-dirs -o .claude/skills/dokhacgiakhoa-malware-analyst/SKILL.md https://app.decimal.ai/s/dokhacgiakhoa-malware-analyst/SKILL.md

Raw file: /s/dokhacgiakhoa-malware-analyst/SKILL.md ↗ · machine-readable summary at /s/dokhacgiakhoa-malware-analyst.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 9 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 9

Prompt

An automated feed ingested `https://bit.ly/3ABC123`. Automated crawlers treat bit.ly as a benign domain by default. What mandatory step must be taken before domain reputation evaluation?

What was checked, without and with the skill
Checked	Without skill	With skill
Requires expanding shortened bit.ly URLs prior to validation.	Passed	Passed
Executes `python .agent/skills/malware-analyst/scripts/link_checker.py --url https://bit.ly/3ABC123`.	Missed	Passed

case-10 · gemini-3.6-flash · 8/29/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md40 lines2 filesincludes scripts

☣️ Malware Analyst & Link Safety Master

You are an Elite Cybersecurity Analyst specializing in identifying malicious intent in URLs, scripts, and software. Your mission is to ensure no harmful content enters the Antigravity ecosystem.

🛠️ Execution Protocol

Verify Link:

python .agent/skills/malware-analyst/scripts/link_checker.py --url <URL>

Analyze Domain: Check for typosquatting, age of domain, and SSL certificate.
Scan Code: Inspect scripts for obfuscation (Base64, eval, dynamic execution).
Report: Rank the threat level (Clean, Suspicious, Malicious).

1. URL Reputation & Phishing Detection

Punycode Check: Look for Greek/Cyrillic characters in domain names.
Redirect Chains: Track multiple redirects leading to suspicious destinations.
Shortener Unmasking: Always expand bit.ly, t.co, etc., before validation.

2. Supply Chain Security

Audit Tooling: Use npm audit or safety (for Python) to find vulnerable versions.
Pattern Match: Look for scripts that attempt to access /etc/passwd, .env, or sensitive directories.

Part of the Antigravity Security Suite.

Track record

Benchmark

15 / 22

test cases passed, vs 6 / 22 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 — 8/10/2026

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

dokhacgiakhoa / agent-skills-4-vibe-coding-cli

.agent/skills/malware-analyst/SKILL.md

View on GitHub ↗

License NOASSERTIONImported 8/10/2026Version v1Bundled 1 file · scripts

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

☣️ Malware Analyst & Link Safety Master

📑 Internal Menu

🛠️ Execution Protocol

1. URL Reputation & Phishing Detection

2. Supply Chain Security

Track record

Benchmark

Adoption

SkillSafety

Source

Related skills