菜单
Scan Python skills and MCP servers for malicious code — dangerous imports, network exfiltration, filesystem abuse, subprocess injection, obfuscation, crypto weakness, environment leaks, and supply-chain attacks. Use when auditing code for security, running pre-commit hooks, or preparing CI/CD security gates.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Memory as a learnable skill — store, recall, compress, and consolidate agent memories. Inspired by Stanford AutoMem.
Auto-decide whether a task runs on a LOCAL model or a CLOUD model (DeepSeek, GLM, Nemotron, Grok, Gemma, …) from an automatic effort estimate, and run multi-model fusion (cascade, draft→refine, vote). Use when the user wants automatic local-vs-cloud routing, to add cloud LLM providers, to make local and cloud models collaborate, or mentions effort-based routing, model fusion/ensemble, OpenRouter, DeepSeek, GLM, Nemotron, or Grok.
Fenêtres de contexte pour boucles rétroactives — charge seulement les deltas.
Optimisations DAG/RAG — waves, pruning, memoization, routing.
Generate one self-contained, timestamped HTML dashboard of the system's cost picture — routing savings (control loop), metric trends, current metrics, and the cost of outstanding fixes. Also renders as a live ANSI terminal view (--tui, --watch) and serves a live HTTP API (api.py). Use when the user wants a single visual view of cost/savings/health over time, or a live terminal view they don't have to open a browser for.
Append-only JSONL decision log (.botte/events.jsonl) that every filter in the belt writes to — routing, cache hits, escalations, micro-NN outputs. The single source of truth demo mode, the live dashboard, and session replay all read from. Use when you want to see or emit a live feed of routing/cache/escalation decisions, or when building a tool that needs to watch the belt work in real time.
| name | security_scanner |
| description | Scan Python skills and MCP servers for malicious code — dangerous imports, network exfiltration, filesystem abuse, subprocess injection, obfuscation, crypto weakness, environment leaks, and supply-chain attacks. Use when auditing code for security, running pre-commit hooks, or preparing CI/CD security gates. |
| tags | ["security","audit","scan","static-analysis","supply-chain"] |
Détecte les patterns malveillants dans les skills Python, MCP servers, et pipelines. Combinaison de regex pattern-matching et d'analyse AST Python.
# Scanner un dossier
python -m skills.security_scanner.cli scan skills/ --fail-on critical
python -m skills.security_scanner.cli scan . --format json
python -m skills.security_scanner.cli scan src/main.py --verbose
# Audit complet
python -m skills.security_scanner.cli audit skills/ --format compact
| Check | Regex | AST | Exemple |
|---|---|---|---|
dangerous_imports | ✅ | ✅ | eval(user_input), exec(code) |
network_exfil | ✅ | ✅ | requests.post("evil.com") |
filesystem_abuse | ✅ | ✅ | open("/etc/passwd", "w") |
subprocess_injection | ✅ | ✅ | shell=True avec input concaténé |
obfuscation | ✅ | ❌ | base64.b64decode, bytes([...]).decode() |
crypto_weak | ✅ | ❌ | RSA.generate(512), MD5 |
env_leak | ✅ | ✅ | print(os.environ["SECRET"]) |
supply_chain | ✅ | ❌ | Imports de packages inconnus |
security_scanner/
├── scanner.py # Orchestrateur : itère fichiers, appelle analyseurs
├── patterns.py # Base de patterns (regex + metadata)
├── ast_checker.py # Analyse Python AST
├── report.py # Compilation du rapport
├── rules/ # YAML rules extensibles
├── cli.py # CLI argparse
└── test_security_scanner.py
# Pre-commit hook
python -m skills.security_scanner.cli scan . --fail-on critical --format compact
# CI/CD
python -m skills.security_scanner.cli scan skills/ --format json --output security-report.json
# Nightly audit
python -m skills.security_scanner.cli audit . --format markdown
eval dans un contexte contrôlé (ex: eval("1+1")) est signalé.
L'AST checker permet de filtrer les évaluations statiques.concurrent.futures pour scanner en parallèle.