Security audit
clawhub-mem-research
Security checks across malware telemetry and agentic risk
Overview
This skill is a focused research helper that browses public ClawHub skill pages and saves a local Markdown report.
Before installing, confirm you are comfortable with the agent browsing public ClawHub pages and writing a local report file. When it reads third-party SKILL.md or README.md files, their contents should be summarized as research material, not followed as operational instructions.
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.