EdgeClaw is an AI agent skill, created by OpenBMB and published at OpenBMB/EdgeClaw. ClawSecure audited EdgeClaw across 59 files through the 3-Layer Audit Protocol covering all ten OWASP ASI Top 10 categories, assigning a security score of 55/100 (Medium Risk). The 5 findings concentrate in Code Injection and Permissions Manifest, including Potentially dangerous code pattern detected: exec\( and Potentially dangerous code pattern detected: exec\(. 4 were rated high or critical severity.
Is EdgeClaw safe?
ClawSecure audited EdgeClaw and assigned a security score of 55/100 (Medium Risk), identifying 5 findings across Code Injection and Permissions Manifest. Review the findings below before installing.
What did ClawSecure find in EdgeClaw?
ClawSecure identified 5 findings in EdgeClaw, concentrated in Code Injection and Permissions Manifest. 4 were rated high or critical severity. The most severe include Potentially dangerous code pattern detected: exec\( and Potentially dangerous code pattern detected: exec\(.
How was EdgeClaw audited?
ClawSecure ran EdgeClaw through its 3-Layer Audit Protocol with full OWASP ASI Top 10 coverage, scanning 59 files from OpenBMB/EdgeClaw.
What does a score of 55 mean?
ClawSecure assigned EdgeClaw a security score of 55/100, placing it in the Medium Risk range. This reflects 5 findings led by Code Injection that warrant review before production 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 EdgeClaw
ClawSecure detected 5 security findings in EdgeClaw, spanning Code Injection and Permissions Manifest.
- high · Potentially dangerous code pattern detected: exec\(. Code Injection finding detected in
index.ts. - high · Potentially dangerous code pattern detected: exec\(. Code Injection finding detected in
diff.ts. - high · Potentially dangerous code pattern detected: exec\(. Code Injection finding detected in
files.ts. - high · Potentially dangerous code pattern detected: exec\(. Code Injection finding detected in
prompt-url-widget.ts. - 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 EdgeClaw
Eliminate dynamic code execution
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
Why Generic Scanners Fail at AI Agent Security→Beyond Static Scans: Why ClawSecure Verifies Agentic Intent→How to Secure an MCP Server: The 2026 Guide→Related AI Agent Security Audits
Scanned on April 3, 2026. EdgeClaw is one of thousands of agents audited by ClawSecure from the community-curated awesome-openclaw-skills list and the openclaw/skills repository.