ClawHub

2026-3-22dataset

v1.0.5

Use for RAGFlow dataset tasks: create, list, inspect, update, or delete datasets; upload, list, update, or delete documents; start or stop parsing; check par...

⭐ 0· 64·0 current·0 all-time
by@redredrrred·duplicate of @redredrrred/rrragflow-skill·canonical: @caesergattuso/1234
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Benign
high confidence
✓
Purpose & Capability
Name/description match the included scripts and env vars: the bundle implements dataset create/list/info/update/delete, document upload/list/update/delete, parsing control, status, search, and model listing. Required env vars (RAGFLOW_API_URL, RAGFLOW_API_KEY) and python3 are appropriate for interacting with a RAGFlow HTTP API.
✓
Instruction Scope
SKILL.md instructs the agent to run the shipped scripts under scripts/ and to prefer --json, and the scripts perform only HTTP calls to the configured RAGFlow URL using the declared env vars. Scripts do not read unrelated system files or other environment variables, and guardrails (resolve IDs first, require explicit delete IDs) are present in policy text.
✓
Install Mechanism
No install spec is provided (instruction-only for runtime usage); scripts are shipped with the skill and executed with python3. No remote downloads or archive extraction are performed by an installer.
✓
Credentials
The only sensitive items requested are RAGFLOW_API_URL and RAGFLOW_API_KEY (primaryEnv), which are directly required to call the service the skill targets. The number and type of env vars are proportionate to the skill's functionality.
✓
Persistence & Privilege
The skill does not request always: true and does not attempt to modify other skills or system-wide agent settings. It requires no persistent installation steps or special privileges beyond running the bundled scripts.
Assessment
This skill appears to do what it advertises: run the included Python scripts against a RAGFlow API. Before installing or enabling it, make sure RAGFLOW_API_URL points to a trusted RAGFlow server and provide only an API key you intend to allow for dataset/document operations. The skill will perform HTTP requests to that URL using the provided key, including endpoints that can list configured LLMs (list_models exposes api_base and other model metadata). The agent's SKILL.md asks you (the agent) to require explicit confirmation for deletes — verify that your agent actually prompts users for confirmation before destructive actions. If you need tighter control, restrict the API key's permissions (principle of least privilege) or use a read-only key for listing/status use cases.

Like a lobster shell, security has layers — review code before you run it.

latestvk97f13p6rkxz0rn2tcfa766ygh83hxe6

License

MIT-0
Free to use, modify, and redistribute. No attribution required.
Termshttps://spdx.org/licenses/MIT-0.html

Runtime requirements

Binspython3
EnvRAGFLOW_API_URL, RAGFLOW_API_KEY
Primary envRAGFLOW_API_KEY

Comments