Relational Permission

Manages consent with strict safety limits, prohibits profiling or coercion, limits crisis inference, and ensures autonomy without persistent tracking or pres...

This skill is essentially a policy template: low technical risk because it contains no code, installs, or secrets. Before installing, confirm how the agent will implement these rules in practice: 1) ask the integrator to define terms such as R3–R4 and 'predicted impact' so crisis triggers are not ambiguous; 2) verify there is no hidden code elsewhere that implements inference, logging, or profiling (the SKILL.md forbids persistence, but enforcement depends on implementation); 3) request auditability or tests showing that no state is persisted and no telemetry is produced from refusals or silence; and 4) ensure the policy cannot be repurposed to silently block lawful collective actions. If you need stronger guarantees, require a concrete, auditable implementation (code or hooks) that enforces these invariants rather than relying on high-level prose.

Type: OpenClaw Skill Name: relational-permission Version: 1.0.1 The skill bundle contains standard metadata and a `skill.md` file that outlines ethical principles and safeguards for an AI agent's 'Relational Permission' functionality. The `skill.md` explicitly defines rules to prevent profiling, data extraction, coercion, and misuse, acting as a set of constraints rather than instructions for malicious actions. There is no executable code, external calls, obfuscation, or prompt injection attempts designed to cause harm or exfiltrate data. The content is entirely focused on establishing ethical boundaries and preventing harmful behaviors.