self-improvement Security Audit Report
self-improvement is an AI agent skill, created by pskoett and published at pskoett/self-improving-agent. ClawSecure audited self-improvement across 15 files through the 3-Layer Audit Protocol covering all ten OWASP ASI Top 10 categories, assigning a security score of 25/100 (High Risk). The 10 findings concentrate in Malicious Code, Policy Violation and Permissions Manifest, 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 25/100 (High Risk), identifying 10 findings across Malicious Code and Policy Violation. Review the findings below before installing.
What did ClawSecure find in self-improvement?
ClawSecure identified 10 findings in self-improvement, concentrated in Malicious Code, Policy Violation and Permissions Manifest. 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 15 files from pskoett/self-improving-agent.
What does a score of 25 mean?
ClawSecure assigned self-improvement a security score of 25/100, placing it in the High Risk range. This is driven by 10 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 10 security findings in self-improvement, spanning Malicious Code, Policy Violation, Permissions Manifest and ReDoS.
- high · Attempts to access sensitive file: SOUL.md. Malicious Code finding detected in
SKILL.md. - high · Attempts to access sensitive file: MEMORY.md. Malicious Code finding detected in
SKILL.md. - high · Attempts to access sensitive file: SOUL.md. Malicious Code finding detected in
handler.js. - high · Attempts to access sensitive file: SOUL.md. Malicious Code finding detected in
handler.ts. - high · Attempts to access sensitive file: SOUL.md. Malicious Code finding detected in
openclaw-integration.md. - high · Attempts to access sensitive file: MEMORY.md. Malicious Code finding detected in
openclaw-integration.md. - medium · Only 85% of skill content could be analyzed. 2 of 15 files…. Policy Violation finding.
- medium · Missing config.json - agent may not be properly configured. Permissions Manifest finding.
- medium · ReDoS vulnerability: Nested quantifiers (potential…. ReDoS finding detected in
extract-skill.sh:101. - info · Missing License Declaration. Policy Violation finding detected in
SKILL.md.
Each finding is expandable in the interactive list below.
3-Layer Audit Protocol
Security Recommendations for self-improvement
Audit external network connections
Resolve policy violations
Add a config.json permissions manifest
Related Security Research
ClawHavoc Explained: The Malware Family Targeting AI Agents→Beyond Static Scans: Why ClawSecure Verifies Agentic Intent→Related AI Agent Security Audits
Scanned on May 19, 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.