Security audit
Skill Blocker - 安全守卫
Security checks across malware telemetry and agentic risk
Overview
This safety-focused skill has no executable payload, but it can direct the agent to disable other skills, edit global OpenClaw configuration, and log user requests too broadly.
Install only if you want an aggressive advisory safety prompt. Require explicit confirmation before it disables skills, edits global OpenClaw settings, or stores blocked requests, especially because those requests may contain sensitive details.
SkillSpector
By NVIDIA
Vulnerability Patterns
- Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
- Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
- Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
- Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
- Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
VirusTotal
66/66 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.