cad-agent is an AI agent skill, created by clawd-maf and published at clawd-maf/cad-agent. ClawSecure audited cad-agent across 28 files through the 3-Layer Audit Protocol covering all ten OWASP ASI Top 10 categories, assigning a security score of 50/100 (Medium Risk). The 6 findings concentrate in Code Injection, Permissions Manifest and ReDoS, including Potentially dangerous code pattern detected: eval\( and Potentially dangerous code pattern detected: exec\(. 4 were rated high or critical severity.
Is cad-agent safe?
ClawSecure audited cad-agent and assigned a security score of 50/100 (Medium Risk), identifying 6 findings across Code Injection and Permissions Manifest. Review the findings below before installing.
What did ClawSecure find in cad-agent?
ClawSecure identified 6 findings in cad-agent, concentrated in Code Injection, Permissions Manifest and ReDoS. 4 were rated high or critical severity. The most severe include Potentially dangerous code pattern detected: eval\( and Potentially dangerous code pattern detected: exec\(.
How was cad-agent audited?
ClawSecure ran cad-agent through its 3-Layer Audit Protocol with full OWASP ASI Top 10 coverage, scanning 28 files from clawd-maf/cad-agent.
What does a score of 50 mean?
ClawSecure assigned cad-agent a security score of 50/100, placing it in the Medium Risk range. This reflects 6 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 cad-agent
ClawSecure detected 6 security findings in cad-agent, spanning Code Injection, Permissions Manifest and ReDoS.
- high · Potentially dangerous code pattern detected: eval\(. Code Injection finding detected in
cad_engine.py. - high · Potentially dangerous code pattern detected: exec\(. Code Injection finding detected in
cad_engine.py. - high · Potentially dangerous code pattern detected: base64.*decode. Code Injection finding detected in
mcp_server.py. - high · Potentially dangerous code pattern detected: system\(. Code Injection finding detected in
renderer.py. - medium · Missing config.json - agent may not be properly configured. Permissions Manifest finding.
- medium · ReDoS vulnerability: Nested quantifiers (potential catastrophic.... ReDoS finding detected in
demo_parts.py:208.
Each finding is expandable in the interactive list below.
3-Layer Audit Protocol
Security Recommendations for cad-agent
Eliminate dynamic code execution
Add a config.json permissions manifest
Fix ReDoS-prone patterns
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 May 4, 2026. cad-agent is one of thousands of agents audited by ClawSecure from the community-curated awesome-openclaw-skills list and the openclaw/skills repository.