polyclaw is an AI agent skill, created by chainstacklabs and published at chainstacklabs/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 45/100 (High Risk). The 6 findings concentrate in Data Exfiltration, Unauthorized Tool Use and Permissions Manifest, including Environment variable harvesting (lib/llm_client.py)… and Multi-File Data Exfiltration Chain. 2 were rated high or critical severity.
Is polyclaw safe?
ClawSecure audited polyclaw and assigned a security score of 45/100 (High Risk), identifying 6 findings across Data Exfiltration and Unauthorized Tool Use. Review the findings below before installing.
What did ClawSecure find in polyclaw?
ClawSecure identified 6 findings in polyclaw, concentrated in Data Exfiltration, Unauthorized Tool Use and Permissions Manifest. 2 were rated high or critical severity. The most severe include Environment variable harvesting (lib/llm_client.py)… and Multi-File Data Exfiltration Chain.
How was polyclaw audited?
ClawSecure ran polyclaw through its 3-Layer Audit Protocol with full OWASP ASI Top 10 coverage, scanning 19 files from chainstacklabs/polyclaw.
What does a score of 45 mean?
ClawSecure assigned polyclaw a security score of 45/100, placing it in the High Risk range. This is driven by 6 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 6 security findings in polyclaw, spanning Data Exfiltration, Unauthorized Tool Use, Permissions Manifest and Policy Violation.
- critical · Environment variable harvesting (lib/llm_client.py)…. Data Exfiltration finding.
- critical · Multi-File Data Exfiltration Chain. Data Exfiltration finding.
- medium · Undeclared Network Access. Unauthorized Tool Use finding detected in
SKILL.md. - medium · Environment Variable Enumeration. Data Exfiltration finding detected in
lib/llm_client.py. - medium · Missing config.json - agent may not be properly configured. Permissions Manifest finding.
- 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 polyclaw
Audit external network connections
Add a config.json permissions manifest
Resolve policy violations
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 9, 2026. polyclaw is one of thousands of agents audited by ClawSecure from the community-curated awesome-openclaw-skills list and the openclaw/skills repository.