wordpress-publisher Security Audit Report
wordpress-publisher is an AI agent skill, created by ClawHub Skill. ClawSecure audited wordpress-publisher across 20 files through the 3-Layer Audit Protocol covering all ten OWASP ASI Top 10 categories, assigning a security score of 30/100 (High Risk). The 14 findings concentrate in Data Exfiltration, ReDoS and Code Injection, including Potentially dangerous code pattern detected: base64.*decode and Undeclared Network Access. 1 was rated high or critical severity.
Is wordpress-publisher safe?
ClawSecure audited wordpress-publisher and assigned a security score of 30/100 (High Risk), identifying 14 findings across Data Exfiltration and ReDoS. Review the findings below before installing.
What did ClawSecure find in wordpress-publisher?
ClawSecure identified 14 findings in wordpress-publisher, concentrated in Data Exfiltration, ReDoS and Code Injection. 1 was rated high or critical severity. The most severe include Potentially dangerous code pattern detected: base64.*decode and Undeclared Network Access.
How was wordpress-publisher audited?
ClawSecure ran wordpress-publisher through its 3-Layer Audit Protocol with full OWASP ASI Top 10 coverage, scanning 20 files.
What does a score of 30 mean?
ClawSecure assigned wordpress-publisher a security score of 30/100, placing it in the High Risk range. This is driven by 14 findings led by Data Exfiltration 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 wordpress-publisher
ClawSecure detected 14 security findings in wordpress-publisher, spanning Data Exfiltration, ReDoS, Code Injection and Unauthorized Tool Use.
- high · Potentially dangerous code pattern detected: base64.*decode. Code Injection finding detected in
wp_publisher.py. - medium · Undeclared Network Access. Unauthorized Tool Use finding detected in
SKILL.md. - medium · Skill performs actions not reflected in its description. Social Engineering finding detected in
SKILL.md. - medium · Outbound HTTP Request Detected. Data Exfiltration finding detected in
scripts/wp_publisher.py:78. - medium · Outbound HTTP Request Detected. Data Exfiltration finding detected in
scripts/wp_publisher.py:82. - medium · Outbound HTTP Request Detected. Data Exfiltration finding detected in
scripts/wp_publisher.py:84. - medium · Outbound HTTP Request Detected. Data Exfiltration finding detected in
scripts/wp_publisher.py:86. - medium · Outbound HTTP Request Detected. Data Exfiltration finding detected in
scripts/wp_publisher.py:88. - medium · File '__init__.py' extension (.py) suggests one format but…. Obfuscation finding detected in
tests/__init__.py. - medium · Suspicious Pattern: pass****. Hardcoded Secrets finding detected in
tests/test_wp_publisher.py:34. - medium · Missing config.json - agent may not be properly configured. Permissions Manifest finding.
- medium · ReDoS vulnerability: Nested quantifiers (potential…. ReDoS finding detected in
wp_publisher.py:389.
Showing the 12 highest-severity of 14 findings. The full interactive list appears below.
3-Layer Audit Protocol
Security Recommendations for wordpress-publisher
Audit external network connections
Fix ReDoS-prone patterns
Eliminate dynamic code execution
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 March 27, 2026. wordpress-publisher is one of thousands of agents audited by ClawSecure from the community-curated awesome-openclaw-skills list and the openclaw/skills repository.