Mc Scan — Development skill for Claude Code
Static-Sweep (MakerChecker mc-scan portiert) fuer UNGESCHUETZTE konsequenzielle Aktionen im EIGENEN Code (.py/.js) — Code-Exec (eval/exec), Shell-Injection (os.system/shell=True), Datei-Loeschung, des.
How to install Mc Scan
Installs to ~/.claude/skills/neo849-a-team-2-mc-scan/SKILL.md
mkdir -p ~/.claude/skills/neo849-a-team-2-mc-scan && curl -fsSL https://raw.githubusercontent.com/NEO849/a-team-2/HEAD/commands/mc-scan.md -o ~/.claude/skills/neo849-a-team-2-mc-scan/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What Mc Scan does
description: Static-Sweep (MakerChecker mc-scan portiert) fuer UNGESCHUETZTE konsequenzielle Aktionen im EIGENEN Code (.py/.js) — Code-Exec (eval/exec), Shell-Injection (os.system/shell=True), Datei-Loeschung, destruktives Git — die keinen Guard (dry-run/confirm/force-check/temp-Pfad/kill-switch) tragen. Deny-by-default aufs eigene Arsenal. Read-only, advisory, aendert nichts. Detektor-/Guard-Dateien per Denylist ausgeschlossen. Trigger "/mc-scan", "ungeschuetzte aktionen im code", "unguarde
Alternatives in Development
- /diagnose — Vérifie l'état de l'environnement RTK et suggère des corrections 25.5k ★
- JWT Scan — JWT attack toolkit (offline) — alg:none forgery, RS256→HS256 algorithm confusion, weak-secret crack, static cl 4.5k ★
- Codex Prompt Handgepflegte Mega Und Mini Prompts — Codex-Prompt — Handgepflegte Mega- und Mini-Prompts fuer alle Plugins 1.5k ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Axguard Inject
Injection and RCE sinks — eval, exec, pickle, shell, child_process. Usage: /axguard-inject [path]
Saphir
Die Notch des MacBooks als Bedienfläche: Claude-Code-Sessions mit Freigaben, Musik, Datei-Regal, Wach halten b
Danger Guard Plugin
Deterministic pre-exec interception of destructive shell commands for OpenClaw agents. Gateway-level pattern m
Signal Claude Bridge
Daemon connects end-to-end encrypted Signal message to a Claude Code agent. Whitelisting, prompt injection mit
Narthex
Prompt-injection defenses for Claude Code. A PreToolUse Bash hook blocks compositional credential-exfiltration
Architect Prove
Run the prove stage. Writes at least ten eval cases including a refusal and an injection case, runs the harnes
Related Agents
Semgrep Triager
Classifies semgrep scan findings as true or false positives by reading source context. Use when triaging stati
Tp Audit Scanner
Use this when the user asks for a security / quality audit, pre-release sweep, or "scan this for issues". Find
Exec Implementer
The implementation worker of stage 4 — receives ONE issue cold and takes it from reading to committed, test-fi