Security audit
Crusoe
Security checks for vulnerabilities and agentic risk
Overview
ClawScan classified the plugin as benign with medium confidence; the completed scan reported no findings, while several dimensions remain notes rather than clear confirmations.
The verdict is benign, but confidence is medium and the scan results do not explain the plugin’s capabilities, installation, or access needs. Review the plugin’s description and requested permissions before installing; a clean scan does not mean risk-free.
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 19, 2026 · 1:33 AM UTC
No reachable vulnerabilities reported
Endor dependency scan completed.
