mcp-skill is an AI agent skill, created by simlocker and published at openclaw/skills. ClawSecure audited mcp-skill across 3 files through the 3-Layer Audit Protocol covering all ten OWASP ASI Top 10 categories, assigning a security score of 95/100 (Safe). The finding concentrates in Permissions Manifest, including Missing config.json - agent may not be properly configured. None were rated high or critical severity.
Is mcp-skill safe?
ClawSecure audited mcp-skill and assigned a security score of 95/100 (Safe), identifying 1 finding across Permissions Manifest. Review the finding below before installing.
What did ClawSecure find in mcp-skill?
ClawSecure identified 1 finding in mcp-skill, concentrated in Permissions Manifest. The most severe is Missing config.json - agent may not be properly configured.
How was mcp-skill audited?
ClawSecure ran mcp-skill through its 3-Layer Audit Protocol with full OWASP ASI Top 10 coverage, scanning 3 files from openclaw/skills.
What does a score of 95 mean?
ClawSecure assigned mcp-skill a security score of 95/100, placing it in the Safe range. Scores of 80 or above qualify for ClawSecure Verified status; the 1 finding detected is lower-severity. 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 mcp-skill
ClawSecure detected 1 security finding in mcp-skill, spanning Permissions Manifest.
- medium · Missing config.json - agent may not be properly configured. Permissions Manifest finding.
Each finding is expandable in the interactive list below.
3-Layer Audit Protocol
Security Recommendations for mcp-skill
Add a config.json permissions manifest
Pin dependencies to exact versions
1.2.3 instead of ^1.2.3) to keep unauthorized code out of your dependency tree. ClawSecure checks every dependency against known CVE databases.Related Security Research
How to Secure an MCP Server: The 2026 Guide→What Is MCP Security? Model Context Protocol Explained→Best AI Agent Security Tools in 2026: How to Choose→Related AI Agent Security Audits
Scanned on April 21, 2026. mcp-skill is one of thousands of agents audited by ClawSecure from the community-curated awesome-openclaw-skills list and the openclaw/skills repository.