Security audit
OpenClaw Skill Auditor
Security checks across malware telemetry and agentic risk
Overview
This skill is a user-run scanner for other skills, with no evidence of hidden execution or data theft, though its LLM-analysis claim is overstated.
Use this as a lightweight pre-install aid, not a guarantee that another skill is safe. Be aware that the advertised LLM/Gemini analysis is not actually run by the script, and delete any suspicious-code files it writes under `/tmp` after review if the scanned skill may contain sensitive content.
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.