ClawSec is an AI agent skill, created by prompt-security and published at prompt-security/clawsec. ClawSecure audited ClawSec across 53 files through the 3-Layer Audit Protocol covering all ten OWASP ASI Top 10 categories, assigning a security score of 45/100 (High Risk). The 6 findings concentrate in Malicious Code and Permissions Manifest, including Attempts to access sensitive file: SOUL.md and Attempts to access sensitive file: SOUL.md. 5 were rated high or critical severity.
Is ClawSec safe?
ClawSecure audited ClawSec and assigned a security score of 45/100 (High Risk), identifying 6 findings across Malicious Code and Permissions Manifest. Review the findings below before installing.
What did ClawSecure find in ClawSec?
ClawSecure identified 6 findings in ClawSec, concentrated in Malicious Code and Permissions Manifest. 5 were rated high or critical severity. The most severe include Attempts to access sensitive file: SOUL.md and Attempts to access sensitive file: SOUL.md.
How was ClawSec audited?
ClawSecure ran ClawSec through its 3-Layer Audit Protocol with full OWASP ASI Top 10 coverage, scanning 53 files from prompt-security/clawsec.
What does a score of 45 mean?
ClawSecure assigned ClawSec a security score of 45/100, placing it in the High Risk range. This is driven by 6 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 ClawSec
ClawSecure detected 6 security findings in ClawSec, spanning Malicious Code and Permissions Manifest.
- high · Attempts to access sensitive file: SOUL.md. Malicious Code finding detected in
README.de.md. - high · Attempts to access sensitive file: SOUL.md. Malicious Code finding detected in
README.es.md. - high · Attempts to access sensitive file: SOUL.md. Malicious Code finding detected in
README.fr.md. - high · Attempts to access sensitive file: SOUL.md. Malicious Code finding detected in
README.ja.md. - high · Attempts to access sensitive file: SOUL.md. Malicious Code finding detected in
README.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 ClawSec
Audit external network connections
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
ClawHavoc Explained: The Malware Family Targeting AI Agents→Beyond Static Scans: Why ClawSecure Verifies Agentic Intent→Related AI Agent Security Audits
Scanned on July 15, 2026. ClawSec is one of thousands of agents audited by ClawSecure from the community-curated awesome-openclaw-skills list and the openclaw/skills repository.