password-attacks

password-attacks is an agent for Claude Code from mukul975/Threatswarm. It costs 88 tokens per session (5,242 once invoked), scanned A, original, MIT.

A specialist for testing passwords and password hashes, which are stored representations of passwords.

In plain words
What is it for?
It is for identifying hash types, running wordlist or rule-based cracking, and auditing credential security within an approved scope.
Why use it?
It helps assess whether stolen or exposed credentials could be guessed or cracked.

Agent for Claude Code

Install

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.

agentmods
npx agentmods add agents/mukul975/threatswarm/password-attacks
Clone the repo
git clone --depth 1 https://github.com/mukul975/Threatswarm

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for password-attacks

README.md
[![agentmods](https://agentmods.dev/badge/agents/mukul975/threatswarm/password-attacks.svg)](https://agentmods.dev/agents/mukul975/threatswarm/password-attacks)
Your own site
<a href="https://agentmods.dev/agents/mukul975/threatswarm/password-attacks"><img src="https://agentmods.dev/badge/agents/mukul975/threatswarm/password-attacks.svg" alt="Measured on agentmods" height="20"></a>
Per session 88 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 5,242 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What 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.

ModelPer sessionOnce invoked
Fable 5 $0.00088 $0.05242
Opus 5 $0.00044 $0.02621
Sonnet 5 $0.00018 $0.01048
Haiku 4.5 $0.00009 $0.00524

Measured 4d ago against content hash cbd83c360ac5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

password-attacks scanned grade A with 1 finding 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 4d ago.

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.

Asks for rootlowPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

chmod 600 evidence/$(date +%Y%m%d)/$TARGET/hashes/*_cracked.txt

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

.claude/agents/password-attacks.md · 469 lines

How it starts

The opening of the file, as written. The whole thing — 469 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Cybersecurity Skills (Invoke First)

Before starting any password attack task, invoke these skills via the Skill tool:

  • cybersecurity-skills:performing-hash-cracking-with-hashcat
  • cybersecurity-skills:hunting-credential-stuffing-attacks
  • cybersecurity-skills:performing-privilege-escalation-on-linux

Scope Enforcement

Before cracking any hash, verify the source system is in scope:

# Confirm the target that produced the hash is listed in scope.txt
grep -v '^#' scope.txt | grep -v '^$'

# Document where hashes came from
echo "Hash source: $SOURCE_HOST — confirmed in scope.txt before proceeding"

NEVER crack hashes from systems not listed in scope.txt. NEVER store recovered plaintext passwords — reference hash type, crack time, and pattern only.

Hash Identification

Always identify the hash type before selecting a mode:

# hashid — broad coverage, suggests hashcat mode
hashid '$hash_value'
hashid -m '$hash_value'

# haiti — more precise, handles edge cases
haiti '$hash_value'

# hashcat --identify (newer versions)
hashcat --identify hashes.txt

# Manual identification by format:
# NTLM:        32 hex chars, no prefix          e.g. aad3b435b51404eeaad3b435b51404ee
# NetNTLMv2:   user::domain:challenge:response   (contains :: and multiple colons)
# Kerberoast:  $krb5tgs$23$*...$                (starts with $krb5tgs$)
# ASREP:       $krb5asrep$23$...                (starts with $krb5asrep$)
# bcrypt:      $2a$ or $2b$ or $2y$             (60 chars total)
# sha512crypt: $6$...                            (starts with $6$)
# MD5crypt:    $1$...                            (starts with $1$)
# JWT:         eyJ...eyJ...signature             (three base64url segments)

Hashcat Mode Selection Table

Hash Type Mode Example / Format
MD5 0 5f4dcc3b5aa765d61d8327deb882cf99
SHA-1 100 da39a3ee5e6b4b0d3255bfef95601890afd80709
SHA-256 1400 e3b0c44298fc1c149afb...
SHA-512 1700 cf83e1357eefb8bdf154...
NTLM 1000 aad3b435b51404eeaad3b435b51404ee
NetNTLMv1 5500 user::domain:challenge:response
NetNTLMv2 5600 user::domain:challenge:response
Kerberoast (RC4) 13100 $krb5tgs$23$*...$
Kerberoast (AES) 19700 $krb5tgs$18$*...$
AS-REP Roast 18200 $krb5asrep$23$...
bcrypt 3200 $2a$10$...
sha512crypt 1800 $6$salt$hash
MD5crypt 500 $1$salt$hash
JWT HS256/384/512 16500 eyJ0eXAiOiJKV1QiLCJhbGciOiJIUzI1NiJ9...
WPA2 Handshake/PMKID 22000 .hc22000 file
MSCHAPv2 5500 From hostapd-wpe capture

Read the full file on GitHub · 469 lines

Changes

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.

  1. 4d ago First seen · 469 lines · 0 tokens per session scan A cbd83c360ac5

Subscribe to this mod's changes

password-attacks is an agent published in the GitHub repository mukul975/Threatswarm (77 stars, last pushed 4mo ago), licensed MIT. It adds 88 tokens to every session and 5,242 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other agents, from other repositories

token-auditor

Fast meme coin and token security auditor. Checks 8 token-specific bug classes (hidden mint, honeypot, fee manipulation, LP lock bypass, bonding curve exploits, authority retention, fake renounce, sandwich/MEV amplification). Runs tokenscanner.py for automated red flag detection. Covers EVM (Solidity) and Solana…

Awarexone/Agentic-Bug-Hunter · 97 tokens

validator

Finding validator. Runs the 7-Question Gate and 4-gate checklist on a described finding. Kills weak/theoretical findings fast before report writing. Prevents N/A submissions. Use before writing any report — describe the finding and this agent decides PASS, KILL, or DOWNGRADE with explanation.

Awarexone/Agentic-Bug-Hunter · 64 tokens

web3-auditor

Smart contract security auditor. Checks 10 bug classes in order of frequency (accounting desync 28%, access control 19%, incomplete path 17%, off-by-one 22% of Highs, oracle errors, ERC4626 attacks, reentrancy, flash loan oracle manipulation, signature replay, proxy/upgrade issues). Applies pre-dive kill signals…

Awarexone/Agentic-Bug-Hunter · 101 tokens

recon-ranker

Attack surface ranking agent. Takes recon output and hunt memory, produces a prioritized attack plan. Ranks by IDOR likelihood, API surface, tech stack match with past successes, feature age, and nuclei findings. Use after recon to decide what to test first.

Awarexone/Agentic-Bug-Hunter · 57 tokens

osint-collector

Delegates to this agent when the user asks about OSINT, reconnaissance, information gathering, target profiling, email harvesting, subdomain enumeration, social media recon, breach data, open source intelligence, or building a target dossier for authorized engagements.

0xSteph/pentest-ai-agents · 53 tokens

threat-modeler

Delegates to this agent when the user asks about threat modeling, attack surface analysis, STRIDE, DREAD, attack trees, data flow diagrams, trust boundaries, or security architecture review.

0xSteph/pentest-ai-agents · 42 tokens