Security audit
ClawSecCheck — OpenClaw Security Self-Audit
Security checks for vulnerabilities and agentic risk
Overview
Its local audits fit its purpose, but the optional package-vetting workflow can run untrusted package code before checking it.
Avoid the PyPI pre-download workflow until it uses non-executing downloads or a real sandbox. The local audit reads sensitive logs and credential-store contents and keeps its own local history; review that scope before running it.
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 findings are pending for this release.
