SecondMind

Autonomous three-tier memory with proactive initiative, project tracking, and social intelligence. Ingests OpenClaw conversations, extracts knowledge + emoti...

SecondMind appears to do exactly what it claims: it reads your OpenClaw session JSONL files, stores local SQLite records, calls OpenRouter for LLM operations, and can notify via Telegram/Discord. Before installing, consider the following: - Review the code and config.json yourself (or in a sandbox) before running setup.js. The repository will create a local data directory (data/secondmind.db) and install cron/Task Scheduler jobs that run every 30 minutes / 6 hours / daily — check and approve those changes. - Keep your OpenRouter API key and Telegram bot token private. The skill asks you to add the OpenRouter key into config.json (or to provide it via an agent prompt); only provide the key if you trust the environment and accept potential API usage/billing. - The skill will capture session contents (including active sessions) during its flush/ingest flows; if you have sensitive conversation content, review what gets stored and where (data/). - Cron jobs and the standalone bot will generate periodic outbound network traffic (OpenRouter API + optional Telegram/Discord). Expect small, recurring API usage and costs; choose model settings carefully. - If you are uncomfortable with persistent background jobs, run the scripts manually for testing (node scripts/status.js, ingest.js, consolidate.js, initiative.js) instead of installing cron/schtasks. Minor metadata note: registry metadata said “no install spec” while SKILL.md includes an npm install step — that mismatch likely reflects metadata staleness but you should verify the install steps prior to running them.

Type: OpenClaw Skill Name: secondmind Version: 1.4.0 The skill is classified as suspicious due to significant shell injection vulnerabilities (RCE risk) present in the `SKILL.md` instructions. The AI agent is explicitly instructed to execute shell commands with user-provided arguments (e.g., `/accept <ID...> [comment]`, `/proposals [filter]`, `/smsearch <query>`). If the OpenClaw agent concatenates user input directly into these commands without proper sanitization, it could lead to arbitrary code execution. Additionally, `AGENT-SETUP.md` poses prompt injection risks by instructing the agent to handle sensitive configuration (API keys, paths) and execute setup scripts. While the core functionality and LLM prompts appear benign and include self-imposed safeguards against sensitive data, these vulnerabilities allow for potential exploitation by a malicious user.