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 fatihkan/badi --skill sc-cmdigit clone --depth 1 https://github.com/fatihkan/badiWrote 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/fatihkan/badi/sc-cmdi)<a href="https://agentmods.dev/skills/fatihkan/badi/sc-cmdi"><img src="https://agentmods.dev/badge/skills/fatihkan/badi/sc-cmdi.svg" alt="Measured on agentmods" 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 | $0.00018 | $0.01295 |
| Opus 5 | $0.00009 | $0.00647 |
| Sonnet 5 | $0.00004 | $0.00259 |
| Haiku 4.5 | $0.00002 | $0.00129 |
Grade B, and why
sc-cmdi scanned grade B with 2 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.
Recursive force deletemediumDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
os.system(f"echo {user_input}") # user_input = "; rm -rf /" Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
"os.system(", "os.popen(", "subprocess.call(", "subprocess.run(", This is a copy
98% identical to sc-cmdi — 1 line 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 — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SC: Command Injection
Purpose
Detects OS command injection vulnerabilities where user-controlled input is passed to system shell commands, subprocess execution, or process spawning functions without proper sanitization. Distinguishes between full command injection (attacker controls the command) and argument injection (attacker controls arguments to a fixed command).
Activation
Called by sc-orchestrator during Phase 2. Runs against all detected languages.
Phase 1: Discovery
File Patterns to Search
**/*.py, **/*.js, **/*.ts, **/*.go, **/*.php, **/*.java, **/*.kt,
**/*.cs, **/*.rb, **/scripts/*, **/*exec*, **/*shell*, **/*command*,
**/*process*, **/*system*, **/*spawn*
Keyword Patterns to Search
# Python
"os.system(", "os.popen(", "subprocess.call(", "subprocess.run(",
"subprocess.Popen(", "subprocess.check_output(", "commands.getoutput(",
"shell=True"
# JavaScript/Node.js
"child_process.exec(", "child_process.execSync(",
"child_process.spawn(", "execFile(", "require('child_process')",
"shelljs", "execa"
# Go
"exec.Command(", "exec.CommandContext(", "os/exec"
# PHP
"exec(", "system(", "passthru(", "shell_exec(", "popen(",
"proc_open(", "pcntl_exec(", "backtick"
# Java
"Runtime.getRuntime().exec(", "ProcessBuilder(",
"new ProcessBuilder("
# C#
"Process.Start(", "ProcessStartInfo(",
"System.Diagnostics.Process"
# Ruby
"system(", "exec(", "IO.popen(", "`"
Data Flow Tracing
Sources: HTTP request parameters, file names from uploads, environment variables from user-controlled sources, database values originally from user input.
Sinks: All command execution functions listed above.
Phase 2: Verification
Command Injection vs Argument Injection
Command injection — attacker controls the full command or can inject shell operators:
# VULNERABLE: Full command injection
os.system(f"echo {user_input}") # user_input = "; rm -rf /"
Argument injection — attacker controls arguments to a known-safe binary:
# VULNERABLE: Argument injection
subprocess.run(["git", "clone", user_url]) # user_url = "--upload-pack=evil"
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 · 159 lines · 18 tokens per session scan B 59f5d37542c2
sc-cmdi is a skill published in the GitHub repository fatihkan/badi (7 stars, last pushed 2d ago), licensed MIT. It adds 18 tokens to every session and 1,295 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 2 findings (recursive force delete, runs shell commands). It is 98% identical to sc-cmdi, differing in 1 line, and is treated as a copy.
Other skills, from other repositories
pr-triage
4-phase PR backlog management with audit, deep code review, validated comments, and optional worktree setup. Use when triaging pull requests, catching up on pending code reviews, or managing a backlog of open PRs. Args: 'all' to review all, PR numbers to focus (e.g. '42 57'), 'en'/'fr' for language, no arg = audit…
audit-agents-skills
Audit Claude Code agents, skills, and commands for quality and production readiness. Use when evaluating skill quality, checking production readiness scores, or comparing agents against best-practice templates.
eval-agents
Audit Claude Code agents defined in .claude/agents/ for description specificity, model tier appropriateness, tools scoping, and system prompt quality. Detects dispatch ambiguity between agents, flags over-permissive tool grants, and checks for human-in-the-loop patterns that break programmatic orchestration. Use when…
issue-triage
3-phase issue backlog management with audit, deep analysis, and validated triage actions. Use when triaging GitHub issues, sorting bug reports, cleaning up stale tickets, or detecting duplicate issues. Args: 'all' to analyze all, issue numbers to focus (e.g. '42 57'), 'en'/'fr' for language, no arg = audit only.
check-cache-bugs
Audit Claude Code setup for cache bugs (CC#40524): sentinel, --resume/--continue, attribution header + ArkNill B3/B4/B5.
git-ai-archaeology
Analyze AI config evolution in a git repo. Use when mapping AI adoption history, finding when configs were first introduced, charting commit velocity by month, or identifying maturity phases in a project's AI tooling.