OpenClaw Health Brief

Generate a daily health brief from Oura, Whoop, and Withings. Unified re-auth script, local token persistence, Green/Yellow/Red morning summary.

This skill's code implements the described functionality, but the manifest omitted important operational requirements. Before installing or enabling it: - Assume this will read secrets from your 1Password vault (via the 'op' CLI) if available and from environment variables otherwise. The skill will persist rotated tokens to ~/.openclaw/secrets/health_tokens.json (it attempts chmod 600). - The skill can also write back refresh tokens to 1Password, but only if you set OPENCLAW_1P_WRITEBACK=1 and have the 'op' CLI and OP_SERVICE_ACCOUNT_TOKEN available — don't enable that flag unless you trust the code and its environment. - The registry metadata did not declare required binaries or env vars; you should verify and install the 'op' CLI yourself and provide only the minimum secrets needed. Consider using environment-only tokens or a dedicated vault/service-account with least privilege. - Review core/util/secrets.py and core/util/local_secrets.py to confirm they behave as you expect (they call subprocess.run('op') and atomically write a JSON file). - If you don't trust the code or the unknown source/owner, don't enable writeback and run the smoke test (./bin/smoke) in an isolated environment first. Ask the publisher for a canonical source repository or homepage before deploying it into production/automated cron jobs.

Type: OpenClaw Skill Name: openclaw-health-brief Version: 1.0.0 This skill bundle is classified as benign. While it involves high-risk capabilities such as reading and writing sensitive OAuth tokens to 1Password (via `op` CLI) and a local file (`~/.openclaw/secrets/health_tokens.json`), and making network requests to external APIs (Oura, Whoop, Withings), these actions are explicitly stated in `SKILL.md` and `README.md`, are necessary for the skill's core functionality (fetching health data and persisting tokens for rotation), and are implemented with security considerations (e.g., opt-in 1Password writeback, `chmod 0o600` for local files). The prompt injection instructions in `SKILL.md` and `README.md` for the AI agent are functional, directing it to process and summarize the skill's output, without any evidence of malicious intent or attempts to manipulate the agent beyond its stated purpose.