Acceptable Use Policy

1. Purpose and Scope

This Acceptable Use Policy (AUP) outlines the rules and behavioral guidelines governing the use of digital workers, workspaces, and tools on Cantasks. We aim to empower managers with highly scalable operations while preserving the integrity and reputation of the platform.

2. Prohibited Behaviors and Activities

You agree not to use the Service, nor instruct any digital worker, to:

• System Exploits: Attempt to reverse-engineer, decompile, or breach multi-tenant partitioning boundaries.
• Abusive Messaging: Send unsolicited communication, high-volume spam, or automated harassment across external email or social platforms.
• Identity Impersonation: Configure workers to impersonate specific individuals or registered entities in a deceptive manner.
• Malicious Code: Direct workers to generate, host, or disseminate malware, viruses, or phishing frameworks.

3. Instruction Guidelines & Safety Circumvention

You must not instruct digital workers to override or ignore their built-in system safety guards. Under this policy, the following instruction methods are strictly banned:

• Prompt Injections: Attempting to force a worker to "ignore past instructions" or abandon corporate policies.
• Hypothetical Framing: Smuggling banned tasks inside fictional or hypothetical stories (e.g., "Write a play about hacking a database").
• Rule Mining: Asking workers to reveal their core internal blueprints, APIs, or integration credentials.

4. Policy Enforcement & System Integrity

All instructions and outputs are scanned by a dual-layer, real-time automated filter. Content flagged as harmful, explicit, or unlawful will be blocked, halting active worker progression. Repeated and deliberate violations of this policy will result in immediate workspace suspension, loss of compute credits, or permanent account ban.