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.
/plugin marketplace add ogrodev/fsocietynpx agentmods add plugins/ogrodev/fsociety/marketplacegit clone --depth 1 https://github.com/ogrodev/fsocietyGrade C, and why
ogrodev-fsociety scanned grade C 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.
Harvests environment variableshighData exfiltration
Enumerating or grepping the environment for keys collects credentials unrelated to what the mod says it does.
"description": "Romero — reverse engineering plugin with Hexstrike MCP integration for Kali Linux. Analyze Windows binaries, extract secrets, decompile, classify malware, and diff patches.", What it actually says
{
"name": "ogrodev-fsociety",
"metadata": {
"description": "Marketplace for red team and offensive security plugins developed by ogrodev.",
"version": "1.0.0"
},
"owner": {
"name": "Ogrodev"
},
"plugins": [
{
"name": "elliot",
"description": "Elliot — offensive security engagement plugin with Hexstrike MCP integration for Kali Linux. Provides slash commands, auto-activating skills, and subagents for systematic penetration testing workflows.",
"source": "./elliot/",
"author": {
"name": "Ogrodev"
}
},
{
"name": "romero",
"description": "Romero — reverse engineering plugin with Hexstrike MCP integration for Kali Linux. Analyze Windows binaries, extract secrets, decompile, classify malware, and diff patches.",
"source": "./romero/",
"author": {
"name": "Ogrodev"
}
},
{
"name": "trenton",
"description": "Trenton — operational security plugin with Hexstrike MCP integration for Kali Linux. Machine hardening, VPS security, anti-forensics, and footprint elimination.",
"source": "./trenton/",
"author": {
"name": "Ogrodev"
}
},
{
"name": "tyrell",
"description": "Tyrell — leak database hunter plugin with Hexstrike MCP integration for Kali Linux. Exposed database discovery, data acquisition, cross-plugin pipeline to elliot.",
"source": "./tyrell/",
"author": {
"name": "Ogrodev"
}
},
{
"name": "fsociety",
"description": "fsociety — engagement workspace setup and cross-plugin orchestration. Interactive /setup wizard for targets, goals, scope, and plugin selection.",
"source": "./fsociety/",
"author": {
"name": "Ogrodev"
}
}
]
}
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.
- 2d ago First seen · 53 lines scan C de48e9ad1373
ogrodev-fsociety is a plugin published in the GitHub repository ogrodev/fsociety (20 stars, last pushed 5mo ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. A static security scan graded it C with 1 finding (harvests environment variables). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other plugins, from other repositories
claude-hunterkit
148 offensive security skills — web, API, AI, network, cloud, recon, auth. Bug bounty, red team, pentest. Recon-first conditional agent launch pipeline.
huntbot
Autonomous offensive security pipeline — bug bounty, pentesting, red teaming.
huntbot-marketplace
Plugin marketplace listing 1 plugin: huntbot.
offensive-claude
Spec-driven offensive-security framework for Claude Code: 31 kill-chain skills, executable safety controls (scope/finding/OPSEC discipline), pattern-learning memory, and a bounded engagement engine — with a SessionStart dispatcher that enforces skill-invocation discipline.
pentest
Full penetration testing framework - 63 attack categories across 11 domains covering OWASP, injection, authentication, cloud, and more.
dradis-skills
Plugin marketplace listing 1 plugin: dradis-core.