Ragie.ai-RAG

Execute Retrieval-Augmented Generation (RAG) using Ragie.ai. Use this skill whenever the user wants to: - Search their knowledge base - Ask questions about u...

What to check before installing: - Metadata mismatch: the registry summary claims no required env/credentials but the SKILL.md and bundled scripts require RAGIE_API_KEY and python3. Confirm which metadata is authoritative and ask the publisher to fix the registry entry before installing. - Secrets: the scripts will send uploaded file contents and metadata to https://api.ragie.ai using whatever RAGIE_API_KEY you provide. Only use an API key you trust to grant that service access to your documents; avoid ingesting secrets or PII unless you trust Ragie. - Local .env: the scripts call load_dotenv() so a local .env file can supply the key. Ensure you don't commit .env to source control and keep the key rotated if compromised. - Dependencies: the package expects requests and python-dotenv. There is no automated installer; ensure the execution environment has python3 and these packages (pip install requests python-dotenv) or run the scripts in an isolated environment. - Inspect & control ingress: ingest.py opens user-specified file paths and posts them to Ragie; review and sanitize any files you plan to upload. Consider running the scripts locally rather than granting broad agent-level execution if you have sensitive data. - If you want higher assurance: ask the publisher to correct registry metadata, provide a reproducible install spec (or a vetted package), and sign the release. If those fixes are made, the skill appears coherent and appropriate for RAG use. Confidence note: medium — the code and instructions are consistent with the described purpose, but the contradictory registry metadata reduces confidence. If registry metadata is corrected to declare RAGIE_API_KEY and python3/requests/python-dotenv, this would increase confidence to high.

Type: OpenClaw Skill Name: ragie-rag Version: 1.0.2 The skill bundle is classified as suspicious due to significant vulnerabilities related to input handling and arbitrary file access, despite lacking explicit malicious intent. The `SKILL.md` instructs the AI agent to execute shell commands with arguments derived from user input (e.g., `--file`, `--url`, `--name`, `--query`), which creates a shell injection risk if the agent does not properly sanitize these inputs. Furthermore, `scripts/ingest.py` allows ingesting arbitrary local files or URLs via the `--file` and `--url` arguments. This could be exploited by a compromised agent to exfiltrate sensitive local files (e.g., `/etc/passwd`, `~/.ssh/id_rsa`) to the legitimate Ragie.ai service, which constitutes an unauthorized data exposure risk. No direct malicious code (e.g., unauthorized exfiltration to third-party domains, backdoors, persistence) was found, and `SKILL.md` even includes instructions to prevent data leakage.