← Back to Scanner

self-improvement Security Audit Report

🔭 Continuously monitored by ClawSecure Watchtower
Source:
SHA-256:

self-improvement is an AI agent skill, created by pskoett and published at openclaw/skills. ClawSecure audited self-improvement across 16 files through the 3-Layer Audit Protocol covering all ten OWASP ASI Top 10 categories, assigning a security score of 19/100 (High Risk). The 13 findings concentrate in Malicious Code, Obfuscation and Policy Violation, including Attempts to access sensitive file: SOUL.md and Attempts to access sensitive file: MEMORY.md. 6 were rated high or critical severity.

Is self-improvement safe?

ClawSecure audited self-improvement and assigned a security score of 19/100 (High Risk), identifying 13 findings across Malicious Code and Obfuscation. Review the findings below before installing.

What did ClawSecure find in self-improvement?

ClawSecure identified 13 findings in self-improvement, concentrated in Malicious Code, Obfuscation and Policy Violation. 6 were rated high or critical severity. The most severe include Attempts to access sensitive file: SOUL.md and Attempts to access sensitive file: MEMORY.md.

How was self-improvement audited?

ClawSecure ran self-improvement through its 3-Layer Audit Protocol with full OWASP ASI Top 10 coverage, scanning 16 files from openclaw/skills.

What does a score of 19 mean?

ClawSecure assigned self-improvement a security score of 19/100, placing it in the High Risk range. This is driven by 13 findings led by Malicious Code 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 self-improvement

ClawSecure detected 13 security findings in self-improvement, spanning Malicious Code, Obfuscation, Policy Violation and Permissions Manifest.

Showing the 12 highest-severity of 13 findings. The full interactive list appears below.

3-Layer Audit Protocol

Security Recommendations for self-improvement

Audit external network connections
self-improvement connects to external endpoints. Verify every outbound connection goes to a trusted destination. Unauthorized callbacks are a primary indicator of ClawHavoc malware and data exfiltration. ClawSecure's proprietary engine monitors for known malicious endpoints including C2 infrastructure.
Review obfuscated or hidden code
self-improvement contains obfuscated or hidden content that resists review. Inspect encoded, minified or hidden files to confirm they are not concealing unexpected behavior before installing.
Resolve policy violations
self-improvement trips ClawSecure policy checks. Review each flagged pattern against your security policy and remediate or document an accepted exception before production use.

Related Security Research

ClawHavoc Explained: The Malware Family Targeting AI Agents→Beyond Static Scans: Why ClawSecure Verifies Agentic Intent→

Related AI Agent Security Audits

openclaw-dashboard-repoScore 25/100@martian-engineering/lossless-clawScore 25/100self-improvementScore 25/100imap-smtp-emailScore 33/100self-improvementScore 25/100

Scanned on March 3, 2026. self-improvement is one of thousands of agents audited by ClawSecure from the community-curated awesome-openclaw-skills list and the openclaw/skills repository.

Start Your Free Scan