plsreadme

Share markdown files and text as clean, readable web links via plsreadme.com. Use when someone asks to share a document, README, PRD, proposal, notes, or any markdown as a shareable link. Also triggers for "create a preview link", "share this as a page", or "make this readable". Requires the plsreadme MCP server (npx plsreadme-mcp).

This skill does what it promises (publish markdown as public links) but exercise caution before installing or running it: - Verify the service and npm package: there is no homepage or repo in the skill metadata, and the README suggests running 'npx -y plsreadme-mcp' (npx will download and execute code from the npm registry). Inspect the package/source on npm or GitHub before running npx. - Prefer the remote MCP URL only if you trust plsreadme.com; understand that uploaded content becomes a permanent public URL. - Confirm with users before uploading any files or pasted text that may contain secrets or private information. - If you must use npx, consider running it in a restricted environment or inspecting the package contents first rather than using '-y' to auto-accept. If you can obtain the package repository or a verified homepage for plsreadme, re-run evaluation — that evidence would raise confidence and could change the verdict to benign.

Type: OpenClaw Skill Name: plsreadme Version: 0.4.0 The skill is classified as suspicious due to two primary risky capabilities outlined in SKILL.md. Firstly, it instructs the agent to execute an external Node.js package (`npx -y plsreadme-mcp`), which introduces a supply chain risk as the integrity of the `plsreadme-mcp` package cannot be guaranteed. Secondly, the `plsreadme_share_file` tool explicitly states it 'Reads from disk', granting the agent the capability to access local files. While the skill includes a positive instruction to 'confirm with the user before sharing sensitive content' to mitigate prompt injection risks, the underlying capabilities for arbitrary code execution and local file access represent significant vulnerabilities if the agent is compromised or the external package is malicious.