◉ Qronos

Decision guidance for life's crossroads. One question. One answer. One moment of clarity.

Before installing: 1) Verify the vendor and source — there is no homepage/source code in the registry entry even though SKILL.md references qronos.ai and terms; ask the developer for a canonical homepage, privacy policy, and source code. 2) Understand data sent: the skill will transmit users' questions, timestamps, and birth dates to api.qronos.ai; only proceed if you trust the service and the human consents. 3) Clarify the QRONOS_API_KEY handling: where is the key stored, who can access it, and why the registry lists 'none' for required env vars. 4) Ask about data retention, logging, and whether the service stores or shares identity/verification data. 5) If you decide to test, do so with non-sensitive example questions and avoid sharing real PII until you confirm the service's privacy and security posture. If these points are not satisfactorily answered, treat the skill as untrusted.

Type: OpenClaw Skill Name: qronos Version: 1.0.7 The OpenClaw AgentSkills skill bundle for 'qronos' is classified as benign. The `SKILL.md` documentation provides clear and robust instructions for the AI agent, actively mitigating common prompt injection risks. It explicitly guides the agent to screen user input for prohibited content (e.g., self-harm, illegal activity) before sending it to the external API, and strictly forbids the agent from modifying, paraphrasing, or adding commentary to the API's response. All external network calls are confined to the `https://api.qronos.ai` domain, and there are no instructions for data exfiltration, unauthorized execution, persistence, or accessing local sensitive files. The instructions emphasize secure handling of the API key and prevent the agent from automating human-only verification steps.