Soulstamp

The stamp doesn't lie. It tells a different truth. Instead of rules, forge your AI a past — a coherent history that makes its behaviors intrinsic, not imposed. Based on Brandon Sanderson's The Emperor's Soul.

This skill is internally consistent: it only guides creation and backup of a local SOUL.md identity file and supplies templates. Before installing or running it: (1) ensure SOUL.md and its backups won't contain secrets (API keys, passwords, private tokens) because those would be stored on disk; (2) review any forged identity you create to make sure it doesn't instruct the assistant to take irreversible external actions or to ignore safety/privacy constraints; (3) consider requiring human confirmation before 'reforge' operations are applied if you want to avoid unexpected behavior changes; and (4) keep backups in a secure location and verify file permissions so backups aren't broadly readable.

Type: OpenClaw Skill Name: soulstamp Version: 1.0.2 The skill is classified as suspicious due to its inherent high-risk capabilities involving direct file system access and the ability to modify the AI agent's core identity and behavior. The `SKILL.md` explicitly instructs the agent to execute shell commands like `cp` for backup purposes and implies read/write/diff operations on the `SOUL.md` file. While these actions are plausibly aligned with the skill's stated purpose of 'soulstamping' the AI, they represent significant control over the agent's environment and self-definition, which could be leveraged for unintended consequences or misuse, even without explicit malicious instructions within the skill bundle itself.