knowledge-graph-memory
Security checks across malware telemetry and agentic risk
Overview
The supplied scan signals show no issues, but the actual target skill artifact was not available in the workspace for a full artifact-backed review.
Treat this as a low-confidence benign result: the available scanners did not flag the skill, but install only after confirming the skill's visible instructions match the behavior you expect and that it does not request unnecessary credentials, broad filesystem access, or automatic background execution.
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.