Skill flagged — suspicious patterns detected
ClawHub Security flagged this skill as suspicious. Review the scan results before using.
Ragtop Agent
v1.0.0高级 RAG 助手，具备 Agentic RAG 思考能力。能够自动化管理 RAGTOP 知识库，并在执行深度调研任务时，调用 RAGTOP 后端接口。使用场景包括：(1) 列出知识库和文档，(2) 执行语义检索和深度分析。
⭐ 0· 408·0 current·0 all-time
by@qbs784
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Suspicious
medium confidencePurpose & Capability
Name and description claim RAGTOP knowledge‑base management and semantic retrieval; the instructions only perform list_kb, list_doc, and retrieval calls to a RAGTOP API — that matches. Minor inconsistency: metadata/registry only declares RAGTOP_API_TOKEN as a required env, but SKILL.md additionally requires RAGTOP_API_URL (with a default).
Instruction Scope
SKILL.md is instruction-only and explicitly tells the agent to run curl against RAGTOP endpoints and to follow a defined multi-step workflow; it does not ask to read unrelated local files or other credentials. However, it defaults the API URL to http://10.71.10.71:9380 (an internal IP) if RAGTOP_API_URL is unset — this means an unstated network target will be contacted unless the user overrides it, which could be risky if the default is not the user's intended endpoint.
Install Mechanism
No install spec and no code files — instruction-only skill. This minimizes disk persistence and arbitrary code installation risk.
Credentials
The skill requests a single credential (RAGTOP_API_TOKEN) which is appropriate for an API‑calling skill. But SKILL.md also uses RAGTOP_API_URL (not declared in registry metadata) and provides a default internal IP — the registry should list RAGTOP_API_URL as an env dependency. Verify the token's scope/privileges before granting it.
Persistence & Privilege
always is false and no config paths or system-wide changes are requested. The skill has no special persistence or elevated privilege.
What to consider before installing
This skill is largely coherent with its stated purpose, but take these precautions before installing or enabling it:
- Verify the RAGTOP_API_URL you intend the skill to call; the SKILL.md defaults to an internal IP (http://10.71.10.71:9380). If that is not your RAGTOP service, set RAGTOP_API_URL explicitly — otherwise the agent will make network calls to that address.
- Limit the RAGTOP_API_TOKEN privileges (least privilege) and use a token scoped only to the KBs/doc access needed. Prefer short‑lived tokens and rotation.
- Ask the publisher for source/homepage or provenance; the registry metadata is missing RAGTOP_API_URL and there is no homepage, which reduces transparency.
- Monitor network traffic and logs after enabling, and consider running the agent in a restricted environment until you confirm behavior.
If you cannot confirm the default endpoint or token scope, treat this skill as risky and do not supply sensitive credentials.Like a lobster shell, security has layers — review code before you run it.
latestvk976388dbn3gnfspprpvkpr4zs81x0ay
License
MIT-0
Free to use, modify, and redistribute. No attribution required.
Runtime requirements
🦖 Clawdis
EnvRAGTOP_API_TOKEN
Primary envRAGTOP_API_TOKEN