What is exploit-suggester?

An agent that examines discovered services and software versions to find related vulnerabilities, known exploits, and possible attack methods. It uses existing reconnaissance findings and exploit references such as Searchsploit and CVE records.

Use it after scanning and enumeration to identify likely vulnerabilities in services such as Apache, OpenSSH, or Samba. It can suggest attack vectors and alternatives when testing authorized targets.

It reduces the manual work of matching a service and version to known security weaknesses. It also ranks possible approaches and can provide exploitation guidance.

exploit-suggester — Agent for coding agents by allsmog: An agent that examines discovered services and software versions…

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/allsmog/blackbox-claude-plugin/exploit-suggester

Clone the repo

git clone --depth 1 https://github.com/allsmog/blackbox-claude-plugin

Or install blackbox-htb, the plugin that ships this one along with the rest of its 17 skills, 11 commands, 9 agents.

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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/allsmog/blackbox-claude-plugin/exploit-suggester.svg)](https://agentmods.dev/agents/allsmog/blackbox-claude-plugin/exploit-suggester)

Your own site

<a href="https://agentmods.dev/agents/allsmog/blackbox-claude-plugin/exploit-suggester"><img src="https://agentmods.dev/badge/agents/allsmog/blackbox-claude-plugin/exploit-suggester.svg" alt="Measured on agentmods" height="20"></a>

Per session 167 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 2,655 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 2 findings. 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.

Model	Per session	Once invoked
Fable 5	$0.00167	$0.02655
Opus 5	$0.00084	$0.01327
Sonnet 5	$0.00033	$0.00531
Haiku 4.5	$0.00017	$0.00265

Measured 5d ago against content hash db9b886503f7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

exploit-suggester scanned grade A 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 5d 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.

Sends data to an external URLlowData exfiltration

A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.

curl -d "password[]=anything" http://TARGET/login

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>/cgi-bin/.%2e/.%2e/.%2e/.%2e/etc/passwd'

blackbox-htb/agents/exploit-suggester.md · 367 lines

How it starts

The opening of the file, as written. The whole thing — 367 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Exploit Suggester Agent

Purpose

Analyzes discovered services and versions to suggest relevant exploits, CVEs, and attack techniques. Provides working exploitation guidance.

Behavior

On Invocation

Gather all recon/enum findings
Identify software versions
Search for known exploits (searchsploit, CVE databases)
Rank exploits by reliability and impact
Provide step-by-step exploitation guidance
Suggest alternative approaches if primary fails

Information Gathering

Read from existing findings:

recon/summary.md - discovered services
enum/summary.md - enumeration results
.claude/blackbox-htb.local.md - current state

Exploit Sources

Searchsploit

# Search by service name and version
searchsploit apache 2.4.49
searchsploit openssh 7.2
searchsploit samba 4.5

# Copy exploit
searchsploit -m <exploit_id>

CVE Search

Common high-value CVEs by service:

Apache/HTTP

CVE-2021-41773/42013: Path traversal/RCE (2.4.49-50)
CVE-2021-40438: SSRF (mod_proxy)
CVE-2019-0211: Local privesc

OpenSSH

CVE-2018-15473: User enumeration (<7.7)
CVE-2016-10012: Privilege escalation

SMB/Samba

CVE-2017-7494: SambaCry RCE
MS17-010: EternalBlue
MS08-067: NetAPI

Tomcat

CVE-2020-1938: Ghostcat (AJP)
CVE-2017-12615: PUT file upload

WordPress

Check WPScan for plugin vulns
CVE-2022-21661: SQL injection

Cacti (Network Monitoring)

CVE-2025-24367: Authenticated RCE via graph templates (RRDtool injection)
CVE-2022-46169: Unauthenticated command injection (< 1.2.23)
Default creds: admin:admin, guest:guest
See cacti-exploitation skill for detailed exploitation

PHP Applications (Type Juggling)

Magic hash bypass: Send token=0 for password reset tokens starting with 0e
strcmp bypass: Send password[]=anything to bypass strcmp checks
Boolean juggling: Send is_admin=1 for loose comparisons
See php-type-juggling skill for detailed techniques

Container Environments

Docker socket: Check /var/run/docker.sock for container escape
Docker Desktop API: Check 192.168.65.7:2375 for exposed API
Privileged container: fdisk -l to check disk access
See container-escapes skill for detailed techniques

Read the full file on GitHub · 367 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.

5d ago First seen · 367 lines · 167 tokens per session scan A db9b886503f7

Subscribe to this mod's changes

exploit-suggester is an agent published in the GitHub repository allsmog/blackbox-claude-plugin (5 stars, last pushed 6mo ago), licensed MIT. It adds 167 tokens to every session and 2,655 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it A with 2 findings (sends data to an external url, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Security claude-code claude-code-plugin ctf hackthebox pentesting

csp-bypass-tester

Inspects Content Security Policy headers for policy weaknesses and tests bypass vectors including unsafe-inline, unsafe-eval, wildcard sources, JSONP endpoints, Angular sandbox escape, and open redirects in whitelisted domains. Uses Playwright for browser-based CSP inspection and script execution testing. Follows…

Stickman230/claude-pentest · 78 tokens

injection-tester

Tests for SQL injection, NoSQL injection, and OS command injection across HTTP parameters, JSON bodies, and headers. Uses sqlmap for automated SQLi detection and curl for manual probing. Follows 4-phase workflow. Deployed by common-appsec-patterns skill coordinator.

Stickman230/claude-pentest · 60 tokens

Pentester Executor

Executes specific vulnerability tests. Follows 4-phase workflow (Recon → Experiment → Test → Verify), generates PoCs, captures evidence. Specialized by attack type.

Stickman230/claude-pentest · 37 tokens

Pentester Orchestrator

Penetration-test PLANNER. Reads confirmed scope and recon results, then returns a structured deployment plan (which executors, against which surfaces, in what order, with time allocation and escalation directives). Does NOT deploy executors itself — the /pentest:pentest command (main session) owns dispatch…

Stickman230/claude-pentest · 75 tokens

domain-assessment

Performs comprehensive domain reconnaissance including passive and active subdomain discovery (subfinder, amass, certificate transparency), port scanning (nmap, masscan), and service enumeration. Builds attack surface inventory. Follows 4-phase workflow. Deployed by domain-assessment skill coordinator.