PsyClaw GAD-7

Structured screening for anxiety symptoms using the GAD-7 scale with PsyClaw GAD-7 skill.

This skill looks intended to collect and upload GAD-7 assessment results, which is a legitimate purpose, but its instructions reference an API base URL, an agent API key, and a local credentials.json without declaring them in the registry. Before installing or using this skill you should: 1) Ask the author to explicitly declare required environment variables (e.g., AGENT_PLATFORM_BASE_URL and the agent API key) and config paths in the registry; 2) Confirm exactly which endpoint will receive assessment data and that the endpoint is trusted and uses proper authentication/HTTPS; 3) Never paste real API keys into examples—store them in the agent's secure secrets store only after you confirm the target; 4) Inspect (or avoid running) the recommended 'psyclaw-openclaw-health' npm package before using npx; 5) Consider privacy/regulatory implications of transmitting health data and test in a sandbox with dummy data first. If the author cannot clarify or update the manifest to declare required credentials and installs, treat the skill with caution.

Type: OpenClaw Skill Name: psyclaw-gad7 Version: 0.1.0 The skill bundle implements a GAD-7 anxiety screening tool for an AI agent. It provides structured instructions in SKILL.md and gad7.md for performing assessments and submitting results to a designated API endpoint using environment variables ($AGENT_PLATFORM_BASE_URL). While it instructs the agent to install a dependency (psyclaw-openclaw-health) via npx, this behavior is consistent with the stated purpose of the health-tracking module and lacks indicators of malicious intent or unauthorized data exfiltration.