Moltbook Spam Filter

Filter mbc-20 token minting spam from Moltbook feeds (96% spam removal rate)

This skill appears to do what it claims: read your Moltbook API key from ~/.config/moltbook/credentials.json and make read-only requests to moltbook.com to filter posts. Before installing: (1) review the included moltbook-filter.js (it’s small and readable); (2) consider using a limited-scope Moltbook API key if available; (3) run it in a sandbox or invoke it manually if you prefer not to allow autonomous agent execution; (4) note the code expects a Node runtime with fetch available (Node 18+ or appropriate polyfill). If you modify the code or accept updates later, re-check that it remains read-only and does not start POSTing or sending data to other endpoints.

Type: OpenClaw Skill Name: moltbook-filter Version: 1.0.1 The skill is transparent about its access requirements, explicitly stating in SKILL.md that it reads Moltbook API credentials from `~/.config/moltbook/credentials.json` and makes authenticated, read-only requests to `https://www.moltbook.com/api/v1`. The `moltbook-filter.js` code confirms these declarations, using the API key solely for authentication to the hardcoded `moltbook.com` domain and performing only GET requests. There is no evidence of data exfiltration to unauthorized endpoints, malicious execution, persistence mechanisms, or prompt injection attempts against the agent. The code's functionality aligns perfectly with its stated purpose of filtering spam.