Security audit
Context Budgeting
Security checks across malware telemetry and agentic risk
Overview
This skill appears to perform the context-management function it advertises, with narrow local memory/checkpoint actions and no evidence of hidden data access or exfiltration.
Before installing, understand that this skill may update local OpenClaw memory/checkpoint state and run its bundled compaction script when context is high. Review the hardcoded workspace path and the script if your OpenClaw setup differs, but the reviewed artifacts do not show hidden or unrelated behavior.
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.