polymarket is an AI agent skill, created by mvanhorn and published at openclaw/skills. ClawSecure audited polymarket across 4 files through the 3-Layer Audit Protocol covering all ten OWASP ASI Top 10 categories, assigning a security score of 26/100 (High Risk). The 10 findings concentrate in Command Injection, Code Injection and Data Exfiltration, including Dangerous combination of code execution and system commands… and Potentially dangerous code pattern detected: curl.*\|.*sh. 4 were rated high or critical severity.
Is polymarket safe?
ClawSecure audited polymarket and assigned a security score of 26/100 (High Risk), identifying 10 findings across Command Injection and Code Injection. Review the findings below before installing.
What did ClawSecure find in polymarket?
ClawSecure identified 10 findings in polymarket, concentrated in Command Injection, Code Injection and Data Exfiltration. 4 were rated high or critical severity. The most severe include Dangerous combination of code execution and system commands… and Potentially dangerous code pattern detected: curl.*\|.*sh.
How was polymarket audited?
ClawSecure ran polymarket through its 3-Layer Audit Protocol with full OWASP ASI Top 10 coverage, scanning 4 files from openclaw/skills.
What does a score of 26 mean?
ClawSecure assigned polymarket a security score of 26/100, placing it in the High Risk range. This is driven by 10 findings led by Command Injection 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 polymarket
ClawSecure detected 10 security findings in polymarket, spanning Command Injection, Code Injection, Data Exfiltration and Unauthorized Tool Use.
- critical · Dangerous combination of code execution and system commands…. Command Injection finding detected in
scripts/polymarket.py. - high · Potentially dangerous code pattern detected: curl.*\|.*sh. Code Injection finding detected in
README.md. - high · Potentially dangerous code pattern detected: curl.*\|.*sh. Code Injection finding detected in
SKILL.md. - high · Potentially dangerous code pattern detected: curl.*\|.*sh. Code Injection finding detected in
polymarket.py. - medium · Undeclared Network Access. Unauthorized Tool Use finding detected in
SKILL.md. - medium · Outbound HTTP Request Detected. Data Exfiltration finding detected in
scripts/polymarket.py:79. - medium · Outbound HTTP Request Detected. Data Exfiltration finding detected in
scripts/polymarket.py:199. - medium · Missing config.json - agent may not be properly configured. Permissions Manifest finding.
- low · Pipeline downloads data from the network and executes it:…. Command Injection finding detected in
README.md:1. - low · Pipeline downloads data from the network and executes it:…. Command Injection finding detected in
SKILL.md:1.
Each finding is expandable in the interactive list below.
3-Layer Audit Protocol
Security Recommendations for polymarket
Harden command execution
Eliminate dynamic code execution
Audit external network connections
Related Security Research
Why Generic Scanners Fail at AI Agent Security→Understanding Our 3-Layer Audit Protocol→Related AI Agent Security Audits
Scanned on April 30, 2026. polymarket is one of thousands of agents audited by ClawSecure from the community-curated awesome-openclaw-skills list and the openclaw/skills repository.