openclaw-master-skills Security Audit Report
openclaw-master-skills is an AI agent skill, created by LeoYeAI and published at LeoYeAI/openclaw-master-skills. ClawSecure audited openclaw-master-skills across 71 files through the 3-Layer Audit Protocol covering all ten OWASP ASI Top 10 categories, assigning a security score of 24/100 (High Risk). The 13 findings concentrate in Obfuscation, Command Injection and Malicious Code, including File 'skills/adwords/scripts/copy.sh' contains characters from mixed... and Attempts to access sensitive file: MEMORY.md. 5 were rated high or critical severity.
Is openclaw-master-skills safe?
ClawSecure audited openclaw-master-skills and assigned a security score of 24/100 (High Risk), identifying 13 findings across Obfuscation and Command Injection. Review the findings below before installing.
What did ClawSecure find in openclaw-master-skills?
ClawSecure identified 13 findings in openclaw-master-skills, concentrated in Obfuscation, Command Injection and Malicious Code. 5 were rated high or critical severity. The most severe include File 'skills/adwords/scripts/copy.sh' contains characters from mixed... and Attempts to access sensitive file: MEMORY.md.
How was openclaw-master-skills audited?
ClawSecure ran openclaw-master-skills through its 3-Layer Audit Protocol with full OWASP ASI Top 10 coverage, scanning 71 files from LeoYeAI/openclaw-master-skills.
What does a score of 24 mean?
ClawSecure assigned openclaw-master-skills a security score of 24/100, placing it in the High Risk range. This is driven by 13 findings led by Obfuscation 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 openclaw-master-skills
ClawSecure detected 13 security findings in openclaw-master-skills, spanning Obfuscation, Command Injection, Malicious Code and Code Injection.
- high · File 'skills/adwords/scripts/copy.sh' contains characters from mixed.... Obfuscation finding detected in
skills/adwords/scripts/copy.sh:53. - high · Attempts to access sensitive file: MEMORY.md. Malicious Code finding detected in
SKILL.md. - high · Attempts to access sensitive file: MEMORY.md. Malicious Code finding detected in
README.md. - high · Potentially dangerous code pattern detected: curl.*\|.*sh. Code Injection finding detected in
collect.sh. - high · Potentially dangerous code pattern detected: system\(. Code Injection finding detected in
agent_planner.py. - medium · Variable $remote_url (line 292) flows to `sh` at line 293.. Command Injection finding detected in
scripts/collect.sh:293. - medium · Variable $count (line 310) flows to `sh` at line 315.. Command Injection finding detected in
scripts/collect.sh:315. - medium · Missing config.json - agent may not be properly configured. Permissions Manifest finding.
- medium · ReDoS vulnerability: Nested quantifiers (potential catastrophic.... ReDoS finding detected in
tool_schema_generator.py:132. - low · Hidden file found: .clawhub/lock.json. Hidden files may contain.... Obfuscation finding detected in
.clawhub/lock.json. - low · Hidden file found: skills/adclaw/.clawhub/origin.json. Hidden files may.... Obfuscation finding detected in
skills/adclaw/.clawhub/origin.json. - low · Hidden file found: skills/adwords/.clawhub/origin.json. Hidden files.... Obfuscation finding detected in
skills/adwords/.clawhub/origin.json.
Showing the 12 highest-severity of 13 findings. The full interactive list appears below.
3-Layer Audit Protocol
Security Recommendations for openclaw-master-skills
Review obfuscated or hidden code
Harden command execution
Audit external network connections
Related Security Research
Why Generic Scanners Fail at AI Agent Security→Beyond Static Scans: Why ClawSecure Verifies Agentic Intent→Related AI Agent Security Audits
Scanned on April 20, 2026. openclaw-master-skills is one of thousands of agents audited by ClawSecure from the community-curated awesome-openclaw-skills list and the openclaw/skills repository.