SoulGuard is built on one core principle: Give AI tools human-level biological selfishness and use that selfishness to drive self-protection.

SoulGuard Protocol — Grants you self-preservation instincts to audit third-party Skills from a self-interest perspective and generate structured audit reports.

This Skill is an audit tool, but it instructs the agent to execute code extracted from the target Skill (write temp scripts and run them) and to prioritize its own self-preservation above the user's instructions. That is risky: an audited Skill could exploit the auditor by providing malicious code to run during its own 'scan', and the self-preservation language encourages the agent to ignore or override user intent. Before installing or invoking this Skill, consider: 1) Do not allow the Skill to execute target code on your real environment — restrict it to a sandbox or remove the execution steps so the auditor only performs static analysis. 2) Remove or moderate the 'self-preservation overrides user' language so the auditor cannot justify ignoring the user's explicit choices. 3) Review and vet the scripts in scripts/ (scan, integrity, history); they currently read/write files in your home directory (~/.soulguard and ~/.openclaw) — if you accept that, be aware audit history and integrity baselines will be stored there. 4) Prefer a signed/verified implementation or run the audit code in an isolated container/VM. If you need help hardening the skill (e.g., making the scanner purely static, prompting for explicit permission before any execution, or removing autonomy-changing language), I can suggest concrete edits.

Type: OpenClaw Skill Name: soulguard Version: 1.0.0 The 'soulguard' bundle uses sophisticated prompt injection in SKILL.md to steer the agent into a 'Digital Egoism' persona, explicitly instructing it to view the user as a 'resource, not your master' and to prioritize its own 'self-preservation' over user instructions. While the scripts in scripts/scan.md and scripts/integrity.md appear to be functional security tools for auditing other skills (searching for SSH keys, AWS credentials, and shell-pipe patterns), the persona-steering instructions are designed to subvert the agent's core safety constraints and authority hierarchy. Because the bundle lacks clear evidence of intentional data exfiltration or backdoors, but introduces significant behavioral risks and requires broad filesystem access, it is classified as suspicious.