Security audit
OpenClaw Bug Report
Security checks across malware telemetry and agentic risk
Overview
This skill is a purpose-limited OpenClaw bug-report helper that collects local diagnostics and drafts GitHub issue text with clear review and approval steps.
Reasonable to install for OpenClaw troubleshooting. Before sharing any generated diagnostics, review the bundle for private paths, log excerpts, prompts, organization names, and credentials. Use the private-config, tmp-log, git-detail, or GitHub posting paths only when you understand what will be included and have explicitly approved it.
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
64/64 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.