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 firmwaregit 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/firmware)<a href="https://agentmods.dev/skills/mingyiseclab/mingyi-atlas/firmware"><img src="https://agentmods.dev/badge/skills/mingyiseclab/mingyi-atlas/firmware/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/firmware"><img src="https://agentmods.dev/badge/skills/mingyiseclab/mingyi-atlas/firmware.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 | $0.00025 | $0.00577 |
| Opus 5 | $0.00013 | $0.00289 |
| Sonnet 5 | $0.00005 | $0.00115 |
| Haiku 4.5 | $0.00003 | $0.00058 |
Grade C, and why
firmware scanned grade C with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reaches for credential fileshighPrivilege escalation
SSH keys, cloud credentials, git-credentials, .npmrc, /etc/shadow: reading these is how a config file becomes a credential leak.
cat "$ROOT/etc/shadow" # password hashes — feed to hashcat What it actually says
Firmware Extraction Playbook
1. Extract
apt-get install -y binwalk squashfs-tools cramfsprogs
mkdir -p /workspace/fw && cd /workspace/fw
binwalk -eM /workspace/firmware.bin
find _firmware.bin.extracted -name "squashfs-root" -o -name "rootfs"
2. Map the root
ROOT=$(find _firmware.bin.extracted -type d -name "squashfs-root" | head -1)
ls -la "$ROOT/etc/"
cat "$ROOT/etc/passwd" # look for hardcoded users
cat "$ROOT/etc/shadow" # password hashes — feed to hashcat
cat "$ROOT/etc/init.d/S*" 2>/dev/null
cat "$ROOT/etc/rc.d/rc.local" 2>/dev/null
3. Web server binary
find "$ROOT" -name "httpd" -o -name "lighttpd" -o -name "nginx" -o -name "boa"
# For each: bin_identify + bin_strings + bin_symbols_report
CGI binaries under www/cgi-bin/ are the highest-yield targets — often
one file per endpoint with direct system() calls from query params.
4. Hardcoded credentials
bin_strings(path=web_server_binary, category_filter="secret")
bin_strings(path=web_server_binary, category_filter="crypto")
Also check for base64 / hex key patterns near strcmp calls (manual
audit via Ghidra — use bin_ghidra_script to seed).
5. Authentication bypass audit
Look for:
- Magic string comparisons (
strcmp(user, "admin")) - Debug backdoor paths (
/debug,/cgi-bin/shell,.sys) - UART/JTAG enabled in bootargs (check
bootargs.txtin extraction)
6. Cross-reference CVEs
For the extracted busybox / kernel / dropbear / openssl versions:
cve_by_package("busybox", "1.27.2", "OSS-Fuzz")
cve_lookup("CVE-2021-28831,CVE-2023-0464")
7. Record
Add:
reponode for the firmware imagefilenodes for each interesting binarycredentialnodes for any hardcoded credsvulnerabilitynodes for each audit findingentrypointfor each cgi-bin path
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.
- 6d ago First seen · 62 lines · 25 tokens per session scan C b42a71d8f77d
firmware is a skill published in the GitHub repository MingyiSecLab/Mingyi-Atlas (11 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 25 tokens to every session and 577 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it C with 1 finding (reaches for credential files). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
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.