Security audit
Universal Translator
Security checks across malware telemetry and agentic risk
Overview
This skill is a disclosed document-translation helper that reads user-selected documents, sends text to the configured LLM for translation, and writes translated output files.
Install only if you are comfortable with document text being processed by your configured LLM, which may be remote depending on your OpenClaw setup. Use explicit input and output folders, avoid broad directories containing sensitive unrelated files, and review translated copies before replacing originals.
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
65/65 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.