polyclaw is an AI agent skill, created by akegaviar and published at akegaviar/polyclaw. ClawSecure audited polyclaw across 19 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 9 findings concentrate in Data Exfiltration, Policy Violation and Unauthorized Tool Use, including Multi-file exfiltration chain detected: lib/llm_client.py collect data... and Environment variable harvesting (lib/llm_client.py) separated from.... 2 were rated high or critical severity.
Is polyclaw safe?
ClawSecure audited polyclaw and assigned a security score of 30/100 (High Risk), identifying 9 findings across Data Exfiltration and Policy Violation. Review the findings below before installing.
What did ClawSecure find in polyclaw?
ClawSecure identified 9 findings in polyclaw, concentrated in Data Exfiltration, Policy Violation and Unauthorized Tool Use. 2 were rated high or critical severity. The most severe include Multi-file exfiltration chain detected: lib/llm_client.py collect data... and Environment variable harvesting (lib/llm_client.py) separated from....
How was polyclaw audited?
ClawSecure ran polyclaw through its 3-Layer Audit Protocol with full OWASP ASI Top 10 coverage, scanning 19 files from akegaviar/polyclaw.
What does a score of 30 mean?
ClawSecure assigned polyclaw a security score of 30/100, placing it in the High Risk range. This is driven by 9 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 polyclaw
ClawSecure detected 9 security findings in polyclaw, spanning Data Exfiltration, Policy Violation, Unauthorized Tool Use and Permissions Manifest.
- critical · Multi-file exfiltration chain detected: lib/llm_client.py collect data.... Data Exfiltration finding.
- critical · Environment variable harvesting (lib/llm_client.py) separated from.... Data Exfiltration finding.
- medium · Pattern detected: import httpx. Data Exfiltration finding detected in
lib/clob_client.py:11. - medium · Pattern detected: import httpx. Data Exfiltration finding detected in
lib/gamma_client.py:7. - medium · Pattern detected: import httpx. Data Exfiltration finding detected in
lib/llm_client.py:10. - medium · Skill code uses network libraries but doesn't declare network.... Unauthorized Tool Use finding.
- medium · Script iterates through environment variables in.... Data Exfiltration finding detected in
/tmp/url-scans/8b544e7c9b26557c/lib/llm_client.py. - medium · Missing config.json - agent may not be properly configured. Permissions Manifest finding.
- info · Skill manifest does not include a 'license' field. Specifying a license.... Policy Violation finding detected in
SKILL.md.
Each finding is expandable in the interactive list below.
3-Layer Audit Protocol
Security Recommendations for polyclaw
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 February 27, 2026. polyclaw is one of thousands of agents audited by ClawSecure from the community-curated awesome-openclaw-skills list and the openclaw/skills repository.