soul-guardian Security Audit Report
soul-guardian is an AI agent skill, created by davida-ps and published at openclaw/skills. ClawSecure audited soul-guardian across 8 files through the 3-Layer Audit Protocol covering all ten OWASP ASI Top 10 categories, assigning a security score of 0/100 (High Risk). The 16 findings concentrate in Malicious Code, Command Injection and Policy Violation, including Pattern detected: subprocess.run(["/bin/launchctl", "bootstrap",... and Pattern detected: subprocess.run(["/bin/launchctl", "enable",.... 13 were rated high or critical severity.
Is soul-guardian safe?
ClawSecure audited soul-guardian and assigned a security score of 0/100 (High Risk), identifying 16 findings across Malicious Code and Command Injection. Review the findings below before installing.
What did ClawSecure find in soul-guardian?
ClawSecure identified 16 findings in soul-guardian, concentrated in Malicious Code, Command Injection and Policy Violation. 13 were rated high or critical severity. The most severe include Pattern detected: subprocess.run(["/bin/launchctl", "bootstrap",... and Pattern detected: subprocess.run(["/bin/launchctl", "enable",....
How was soul-guardian audited?
ClawSecure ran soul-guardian through its 3-Layer Audit Protocol with full OWASP ASI Top 10 coverage, scanning 8 files from openclaw/skills.
What does a score of 0 mean?
ClawSecure assigned soul-guardian a security score of 0/100, placing it in the High Risk range. This is driven by 16 findings led by Malicious Code that should be addressed before use. ClawSecure derives this score with a weighted deduction model (critical -20, high -10, medium -5, low -2 from a base of 100).
Audit Findings for soul-guardian
ClawSecure detected 16 security findings in soul-guardian, spanning Malicious Code, Command Injection, Policy Violation and Skill Discovery Abuse.
- critical · Pattern detected: subprocess.run(["/bin/launchctl", "bootstrap",.... Command Injection finding detected in
scripts/install_launchd_plist.py:144. - critical · Pattern detected: subprocess.run(["/bin/launchctl", "enable",.... Command Injection finding detected in
scripts/install_launchd_plist.py:151. - critical · Pattern detected: subprocess.run(["/bin/launchctl", "kickstart", "-k",.... Command Injection finding detected in
scripts/install_launchd_plist.py:152. - high · Attempts to access sensitive file: SOUL.md. Malicious Code finding detected in
README.md. - high · Attempts to access sensitive file: MEMORY.md. Malicious Code finding detected in
README.md. - high · Attempts to access sensitive file: SOUL.md. Malicious Code finding detected in
SKILL.md. - high · Attempts to access sensitive file: MEMORY.md. Malicious Code finding detected in
SKILL.md. - high · Attempts to access sensitive file: SOUL.md. Malicious Code finding detected in
onboard_state_dir.py. - high · Attempts to access sensitive file: MEMORY.md. Malicious Code finding detected in
onboard_state_dir.py. - high · Attempts to access sensitive file: SOUL.md. Malicious Code finding detected in
soul_guardian.py. - high · Attempts to access sensitive file: MEMORY.md. Malicious Code finding detected in
soul_guardian.py. - high · Attempts to access sensitive file: SOUL.md. Malicious Code finding detected in
test_soul_guardian.py.
Showing the 12 highest-severity of 16 findings. The full interactive list appears below.
3-Layer Audit Protocol
Security Recommendations for soul-guardian
Audit external network connections
Harden command execution
Resolve policy violations
Related Security Research
ClawHavoc Explained: The Malware Family Targeting AI Agents→Beyond Static Scans: Why ClawSecure Verifies Agentic Intent→Related AI Agent Security Audits
Scanned on February 7, 2026. soul-guardian is one of thousands of agents audited by ClawSecure from the community-curated awesome-openclaw-skills list and the openclaw/skills repository.