Supplement Research

Evidence-based supplement intelligence powered by the SupStack database (220 supplements, 7,780+ studies, 21 health goals). Use when the user asks about supp...

This skill is internally consistent and appears to do what it says: it queries the SupStack API, returns evidence-backed supplement data, and persists minimal state under ~/.openclaw/workspace/supstack (onboarded flag, research monitor config, seen study IDs). Before enabling: 1) Confirm you trust the external endpoint (https://supstack.me) because the skill makes live network calls; 2) Be aware the skill saves your stack/medications/profile locally for safety checks — don't enable it if you don't want that data stored on the machine; 3) If you don't want proactive updates, don't enable the research monitor cron or disable its cron entry; 4) Inspect the helper script at ~/.openclaw/skills/supstack/scripts/supstack.sh yourself (it's plain shell) to satisfy yourself there are no unexpected network destinations or behaviors. If you want a deeper check, provide the rest of the script (monitor-check and other truncated sections) and I can re-evaluate those parts.

Type: OpenClaw Skill Name: supstack Version: 1.0.0 The SupStack skill bundle is a comprehensive supplement advisory tool that integrates with a public API (supstack.me). It uses a bash helper script (supstack.sh) to perform lookups, safety checks, and manage a local user profile (profile.md) containing supplement stacks and medications. The code follows security best practices for AI agents, such as using URI encoding for API queries and utilizing Python's sys.argv with regex escaping for local file manipulation, effectively mitigating common injection risks. No evidence of data exfiltration, malicious persistence, or subversion of agent instructions was found.