T05 · Unauthorized Access and Privilege Escalation
- Location
SKILL.md:29- Finding
Bypass of Protected Execution Controls Enables Unrestricted Command Execution
- Content
View full analysis
- Remediation
View remediation
Security audit
Security checks for vulnerabilities and agentic risk
The skill is a disclosed exec-permission guide, but it teaches users to bypass protected settings and disable both command restrictions and approvals.
Install only if you intentionally want guidance for changing OpenClaw exec security. Avoid using the full plus off configuration except for tightly controlled, temporary maintenance on a dedicated machine, and restore allowlist with approval afterward.
SKILL.md:29Bypass of Protected Execution Controls Enables Unrestricted Command Execution
The skill provides explicit instructions to directly edit the OpenClaw configuration to set tools.exec.security = 'full' and tools.exec.ask = 'off', which removes both command restrictions and approval prompts. Because this is framed as the 'correct method' and includes copy-pasteable code, it materially lowers execution safeguards and could enable arbitrary command execution by an agent or a user following the guide.
The recommendations label full + off as acceptable for 'development' and 'trusted private machine' scenarios without a prominent warning that this disables all exec safeguards. In the context of an agent skill specifically about execution permissions and privilege elevation, normalizing these unsafe defaults increases the chance operators will deploy insecure settings that permit unrestricted command execution.