中文 EN

扫描报告

扫描新文件

⚠ 低风险 — 风险评分 15/100
上次扫描：1 天前 重新扫描
15 /100
automation-workflows
Design and implement automation workflows to save time and scale operations as a solopreneur
This is a legitimate automation-workflows skill for solopreneurs containing agent management, messaging, and cognitive memory scripts with no malicious behavior detected.
技能名称automation-workflows
分析耗时51.9s
引擎pi
✓
可以安装
Approve for use. All scripts perform documented, benign operations (Telegram notifications, Discord channel management, Tavily search, ElevenLabs transcription). No credential theft, exfiltration, or obfuscation observed.

安全发现 3 项

严重性 安全发现 位置
低危
Hardcoded user-specific paths 敏感访问
Several scripts reference C:\Users\Luffy\ paths and ~ for a specific user. This is a portability concern rather than a security issue, as the scripts are designed for a specific local installation of the OpenClaw toolchain.
LOG_DIR = Path("C:/Users/Luffy/clawd/logs")
→ Use environment variables or config file for log directory path instead of hardcoded user path.
 scripts/send_status_with_logging.py:19
低危
Hardcoded Telegram target ID 敏感访问
Telegram target ID 7590912486 is hardcoded as default across multiple send_status scripts. While this is not credential theft, it means messages go to a specific user by default.
target = os.environ.get("TELEGRAM_TARGET", "7590912486")
→ Make target entirely environment-driven with no fallback to avoid accidental message routing.
 scripts/send_status.py:62
低危
SKILL.md declares no tools but scripts use subprocess and network APIs 文档欺骗
SKILL.md is purely instructional documentation about automation workflows (no-code tools like Zapier/Make/n8n). It makes no capability declarations. The supporting scripts use subprocess and HTTP APIs, which is appropriate for the OpenClaw integration purpose.
Design and implement automation workflows to save time and scale operations as a solopreneur
→ This is not a true doc-to-code mismatch since SKILL.md is not intended to describe script capabilities - it's a human-facing workflow guide. No action needed.
 SKILL.md:1
资源类型声明权限推断权限状态证据
网络访问 NONE READ ✓ 一致 search.mjs:98 makes HTTPS POST to api.tavily.com; transcribe.sh:71 makes HTTPS P…
文件系统 NONE WRITE ✓ 一致 create-agent.sh:59-64 creates workspace directories; init_memory.sh:22-24 create…
命令执行 NONE WRITE ✓ 一致 send_status.py:73-87 runs clawdbot CLI via subprocess; create-agent.sh:107 calls…
环境变量 NONE READ ✓ 一致 search.mjs:87 reads TAVILY_API_KEY; transcribe.sh:47 reads ELEVENLABS_API_KEY; s…
10 项发现
🔗
中危 外部 URL 外部 URL
https://openclaw.ai
README.md:3
🔗
中危 外部 URL 外部 URL
https://docs.openclaw.ai
README.md:538
🔗
中危 外部 URL 外部 URL
https://discord.com/invite/clawd
README.md:539
🔗
中危 外部 URL 外部 URL
https://clawhub.com
README.md:540
🔗
中危 外部 URL 外部 URL
https://staging.example.com
ci-cd.md:137
🔗
中危 外部 URL 外部 URL
https://discord.com/api/v10/channels/
scripts/rename_channel.py:51
🔗
中危 外部 URL 外部 URL
https://tavily.com
scripts/search.mjs:84
🔗
中危 外部 URL 外部 URL
https://api.tavily.com/search
scripts/search.mjs:100
🔗
中危 外部 URL 外部 URL
https://discord.com/api/v10/guilds/
scripts/setup_channel.py:51
🔗
中危 外部 URL 外部 URL
https://api.elevenlabs.io/v1/speech-to-text
scripts/transcribe.sh:71

目录结构

66 文件 · 289.3 KB · 9328 行
Markdown 49f · 6452L Shell 6f · 1370L Python 8f · 1327L JavaScript 1f · 150L JSON 2f · 29L
├─ ▾ 📁 assets
│ ├─ ▾ 📁 templates
│ │ ├─ 📝 agents-memory-block.md Markdown 227L · 7.2 KB
│ │ ├─ 📋 decay-scores.json JSON 24L · 539 B
│ │ ├─ 📝 entity-template.md Markdown 20L · 348 B
│ │ ├─ 📝 episode-template.md Markdown 7L · 279 B
│ │ ├─ 📝 evolution.md Markdown 35L · 761 B
│ │ ├─ 📝 graph-index.md Markdown 11L · 317 B
│ │ ├─ 📝 IDENTITY.md Markdown 68L · 1.9 KB
│ │ ├─ 📝 MEMORY.md Markdown 30L · 850 B
│ │ ├─ 📝 pending-memories.md Markdown 18L · 511 B
│ │ ├─ 📝 pending-reflection.md Markdown 54L · 1.7 KB
│ │ ├─ 📝 procedure-template.md Markdown 18L · 321 B
│ │ ├─ 📝 reflection-log.md Markdown 28L · 579 B
│ │ ├─ 📝 relations.md Markdown 18L · 508 B
│ │ ├─ 📝 reward-log.md Markdown 10L · 256 B
│ │ ├─ 📝 reward-template.md Markdown 55L · 1.0 KB
│ │ └─ 📝 SOUL.md Markdown 97L · 3.2 KB
│ └─ 📝 operator-prompts.md Markdown 14L · 382 B
├─ ▾ 📁 references
│ ├─ 📝 architecture.md Markdown 1274L · 54.8 KB
│ ├─ 📝 command-cheatsheet.md Markdown 13L · 157 B
│ ├─ 📝 failure-handling.md Markdown 13L · 305 B
│ ├─ 📝 model-selection.md Markdown 15L · 320 B
│ ├─ 📝 plan-vs-build.md Markdown 17L · 251 B
│ ├─ 📝 question-handling.md Markdown 8L · 195 B
│ ├─ 📝 reflection-process.md Markdown 1186L · 40.7 KB
│ ├─ 📝 routing-prompt.md Markdown 67L · 1.7 KB
│ ├─ 📝 session-management.md Markdown 10L · 328 B
│ ├─ 📝 usage.md Markdown 201L · 5.2 KB
│ └─ 📝 workflow.md Markdown 12L · 336 B
├─ ▾ 📁 scripts
│ ├─ 🔧 create-agent.sh Shell 352L · 8.5 KB
│ ├─ 🔧 init_memory.sh Shell 147L · 5.1 KB
│ ├─ 🐍 monitor_task.py Python 273L · 9.1 KB
│ ├─ 🐍 rename_channel.py Python 192L · 6.6 KB
│ ├─ 📜 search.mjs JavaScript 150L · 3.9 KB
│ ├─ 🐍 send_status_websocket.py Python 113L · 3.1 KB
│ ├─ 🐍 send_status_with_logging.py Python 215L · 6.7 KB
│ ├─ 🐍 send_status.py Python 180L · 5.4 KB
│ ├─ 🐍 setup_channel.py Python 178L · 6.0 KB
│ ├─ 🐍 test_send_status.py Python 62L · 1.9 KB
│ ├─ 🔧 transcribe.sh Shell 104L · 2.3 KB
│ ├─ 🔧 upgrade_to_1.0.6.sh Shell 298L · 9.1 KB
│ └─ 🔧 upgrade_to_1.0.7.sh Shell 234L · 7.7 KB
├─ 📋 _meta.json JSON 5L · 139 B
├─ 📝 boundaries.md Markdown 59L · 2.2 KB
├─ 📝 ci-cd.md Markdown 176L · 3.4 KB
├─ 📝 corrections.md Markdown 36L · 1.0 KB
├─ 📝 debugging.md Markdown 136L · 3.5 KB
├─ 🐍 examples.py Python 114L · 3.1 KB
├─ 📝 heartbeat-rules.md Markdown 54L · 1.8 KB
├─ 📝 heartbeat-state.md Markdown 22L · 584 B
├─ 📝 HEARTBEAT.md Markdown 5L · 261 B
├─ 📝 learning.md Markdown 106L · 2.9 KB
├─ 📝 memory-template.md Markdown 75L · 1.2 KB
├─ 📝 memory.md Markdown 30L · 756 B
├─ 📝 openclaw-heartbeat.md Markdown 5L · 261 B
├─ 📝 operations.md Markdown 144L · 3.4 KB
├─ 📝 README.md Markdown 558L · 12.8 KB
├─ 📝 reflections.md Markdown 31L · 840 B
├─ 📝 scaling.md Markdown 125L · 2.9 KB
├─ 📝 scraping.md Markdown 139L · 3.9 KB
├─ 📝 selectors.md Markdown 84L · 2.3 KB
├─ 📝 setup.md Markdown 196L · 6.2 KB
├─ 📝 SKILL.md Markdown 267L · 10.1 KB
├─ 📝 testing.md Markdown 148L · 4.4 KB
├─ 🔧 upgrade_to_1.0.7.sh Shell 235L · 7.7 KB
├─ 📝 UPGRADE-1.0.7.md Markdown 265L · 6.8 KB
└─ 📝 UPGRADE.md Markdown 265L · 6.8 KB

依赖分析 1 项

包名版本来源已知漏洞备注
websocket-client unpinned pip 否 Used for Telegram WebSocket integration; no version constraint specified

安全亮点

✓ No base64-encoded or obfuscated code anywhere in the codebase
✓ No reverse shell, C2, or remote code execution mechanisms
✓ No credential harvesting or exfiltration - only legitimate third-party API calls (Tavily search, ElevenLabs STT, Discord API, Telegram WebSocket)
✓ No access to ~/.ssh, ~/.aws, or other sensitive credential paths
✓ No curl|bash or wget|sh remote script execution patterns
✓ All network calls go to known, legitimate third-party services over HTTPS
✓ subprocess usage is limited to local CLI tools (openclaw, clawdbot) which are part of the OpenClaw toolchain
✓ API keys read from environment variables only, not harvested from files or sent to third parties
✓ Backup operations in upgrade scripts before destructive changes
✓ Git-based audit trail via init_memory.sh