Security audit
OpenShell Sandbox
Security checks for vulnerabilities and agentic risk
Overview
ClawScan rates openshell benign with medium confidence; the completed scanner reported no findings, while the verdict notes some installation and persistence considerations.
The verdict is benign, not a guarantee of zero risk. The scan completed without reported findings, but confidence is medium, and the installation and persistence notes are not explained in the available results. Review the plugin’s setup and permissions before installing.
Vulnerability Patterns
- Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
- Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
- Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
- Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
- Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
SkillSpector was not run because this plugin release contains no bundled skills.
Endor dependency reachability
Checked Nov 16, 2026 · 2:34 AM UTC
No reachable vulnerabilities reported
Endor dependency scan completed.
