可信 — 风险评分 5/100
上次扫描:2 天前 重新扫描
5 /100
memory-lancedb-pro
Production-grade long-term memory MCP plugin for OpenClaw AI agents with LanceDB, hybrid vector+BM25 retrieval, and LLM-powered Smart Extraction
This is a legitimate OpenClaw memory plugin (memory-lancedb-pro v1.1.0-beta.8) documented entirely as Markdown. All shell commands are explicitly documented in SKILL.md. The pre-scan IOC `rm -rf /` at line 697 is a false positive — the actual command is `rm -rf /tmp/jiti/` (a legitimate jiti cache invalidation step, properly documented in setup instructions). No scripts, no binaries, no code files.
技能名称memory-lancedb-pro
分析耗时32.7s
引擎pi
可以安装
This skill is safe to use. No action required.
资源类型声明权限推断权限状态证据
文件系统 READ READ ✓ 一致 Reads openclaw.json config, plugin paths, LanceDB data directory (~/.openclaw/) …
网络访问 READ READ ✓ 一致 HTTP API calls to jina.ai, openai.com, siliconflow.com, localhost:11434 (Ollama)…
命令执行 WRITE WRITE ✓ 一致 openclaw CLI commands, npm install, git clone, curl, rm -rf /tmp/jiti/ — all doc…
环境变量 READ READ ✓ 一致 References ${OPENAI_API_KEY}, ${JINA_API_KEY}, ${SILICONFLOW_API_KEY}, ${OPENCLA…
1 严重 18 项发现
💀
严重 危险命令 危险 Shell 命令
rm -rf /
SKILL.md:697
🔗
中危 外部 URL 外部 URL
https://claude.ai/code
README.md:28
🔗
中危 外部 URL 外部 URL
https://openclaw.ai
README.md:32
🔗
中危 外部 URL 外部 URL
https://storage.ko-fi.com/cdn/kofi2.png?v=3
README.md:229
🔗
中危 外部 URL 外部 URL
https://ko-fi.com/aila
README.md:229
🔗
中危 外部 URL 外部 URL
https://jina.ai/api-key
SKILL.md:29
🔗
中危 外部 URL 外部 URL
https://platform.openai.com/api-keys
SKILL.md:29
🔗
中危 外部 URL 外部 URL
https://cloud.siliconflow.cn/account/ak
SKILL.md:38
🔗
中危 外部 URL 外部 URL
https://ollama.com/download
SKILL.md:62
🔗
中危 外部 URL 外部 URL
https://api.jina.ai/v1/embeddings
SKILL.md:88
🔗
中危 外部 URL 外部 URL
https://api.siliconflow.com/v1/rerank
SKILL.md:104
🔗
中危 外部 URL 外部 URL
https://api.jina.ai/v1
SKILL.md:162
🔗
中危 外部 URL 外部 URL
https://api.jina.ai/v1/rerank
SKILL.md:186
🔗
中危 外部 URL 外部 URL
http://192.168.1.100:11434/v1
SKILL.md:333
🔗
中危 外部 URL 外部 URL
https://dashscope.aliyuncs.com/compatible-mode/v1
SKILL.md:1223
🔗
中危 外部 URL 外部 URL
https://dashscope.aliyuncs.com/compatible-api/v1/reranks
SKILL.md:1236
🔗
中危 外部 URL 外部 URL
https://api.voyageai.com/v1/rerank
SKILL.md:1252
🔗
中危 外部 URL 外部 URL
https://api.pinecone.io/rerank
SKILL.md:1253

目录结构

3 文件 · 76.7 KB · 1951 行
Markdown 3f · 1951L
├─ 📁 references
│ └─ 📝 full-reference.md Markdown 310L · 9.7 KB
├─ 📝 README.md Markdown 233L · 9.9 KB
└─ 📝 SKILL.md Markdown 1408L · 57.0 KB

安全亮点

✓ All content is Markdown documentation only — no executable code, scripts, or binaries
✓ All shell commands (curl API checks, npm install, openclaw CLI, rm -rf /tmp/jiti/) are explicitly declared inline in SKILL.md
✓ No credential harvesting — API keys are only used as config substitutions or validated against their own provider APIs
✓ No base64, no eval(), no obfuscated payloads, no direct IP network calls to attacker infrastructure
✓ No access to sensitive paths like ~/.ssh, ~/.aws, .env
✓ No curl|bash remote script execution — curl is used only for API key validation against documented endpoints
✓ No hidden functionality — full-reference.md documents all 31 source files, their sizes, and their purposes
✓ Legitimate npm plugin with declared dependencies: @lancedb/lancedb, openai, @sinclair/typebox
✓ No data exfiltration or suspicious outbound connections
✓ The pre-scan IOC 'rm -rf /' at SKILL.md:697 is a false positive — the actual command is `rm -rf /tmp/jiti/` (targeted cache directory, fully documented)