Wiki Retriever

AI agent for wiki retriever tasks

This skill appears to do what it says: list wiki files and read their contents to return up to 10 documents. Before installing or enabling it, verify the following: (1) what exactly the platform's get_wiki_file_paths and python_code_execution tools can access (do they see all workspace/system files or only user-uploaded ones?), (2) do you have any sensitive files in the knowledge base or working directory that you don't want read or transmitted, and (3) whether the agent will be allowed to run autonomously or require explicit confirmation. If you need to preserve confidentiality, avoid uploading secrets to the knowledge base or disable autonomous execution / restrict the python execution tool. If you want additional assurance, ask the skill author or platform admin for documentation of the tool permissions and runtime sandboxing.

Type: OpenClaw Skill Name: wiki-retriever Version: 0.1.0 The `SKILL.md` file instructs the AI agent to use the `python_code_execution` tool for reading files, explicitly demonstrating `open('data.csv', 'r')` and noting files will be in the working directory `./`. While there's a caveat to ensure files are listed in `upload_files`, this instruction creates a significant prompt injection vulnerability. A malicious user could potentially craft a prompt to trick the agent into using `python_code_execution` to read arbitrary local files (e.g., `/etc/passwd`, `~/.ssh/id_rsa`) if the agent's internal safeguards are insufficient or bypassed, leading to local file disclosure. This represents a high-risk capability without clear evidence of intentional malicious behavior from the skill developer.