claude-mem is an AI agent skill, created by thedotmack and published at thedotmack/claude-mem. ClawSecure audited claude-mem across 52 files through the 3-Layer Audit Protocol covering all ten OWASP ASI Top 10 categories, assigning a security score of 35/100 (High Risk). The 7 findings concentrate in Code Injection, Malicious Code and Permissions Manifest, including Attempts to access sensitive file: MEMORY.md and Attempts to access sensitive file: MEMORY.md. 6 were rated high or critical severity.
Is claude-mem safe?
ClawSecure audited claude-mem and assigned a security score of 35/100 (High Risk), identifying 7 findings across Code Injection and Malicious Code. Review the findings below before installing.
What did ClawSecure find in claude-mem?
ClawSecure identified 7 findings in claude-mem, concentrated in Code Injection, Malicious Code and Permissions Manifest. 6 were rated high or critical severity. The most severe include Attempts to access sensitive file: MEMORY.md and Attempts to access sensitive file: MEMORY.md.
How was claude-mem audited?
ClawSecure ran claude-mem through its 3-Layer Audit Protocol with full OWASP ASI Top 10 coverage, scanning 52 files from thedotmack/claude-mem.
What does a score of 35 mean?
ClawSecure assigned claude-mem a security score of 35/100, placing it in the High Risk range. This is driven by 7 findings led by Code Injection 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 claude-mem
ClawSecure detected 7 security findings in claude-mem, spanning Code Injection, Malicious Code and Permissions Manifest.
- high · Attempts to access sensitive file: MEMORY.md. Malicious Code finding detected in
npx-distribution.md. - high · Attempts to access sensitive file: MEMORY.md. Malicious Code finding detected in
CHANGELOG.md. - high · Potentially dangerous code pattern detected: curl.*\|.*sh. Code Injection finding detected in
animated-installer.md. - high · Potentially dangerous code pattern detected: curl.*\|.*sh. Code Injection finding detected in
CHANGELOG.md. - high · Potentially dangerous code pattern detected: curl.*\|.*sh. Code Injection finding detected in
README.md. - high · Potentially dangerous code pattern detected: curl.*\|.*sh. Code Injection finding detected in
STANDALONE-SETUP.md. - 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 claude-mem
Eliminate dynamic code execution
Audit external network connections
Add a config.json permissions manifest
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 August 8, 2026. claude-mem is one of thousands of agents audited by ClawSecure from the community-curated awesome-openclaw-skills list and the openclaw/skills repository.