Knowledge Graph Hardened

Security checks across malware telemetry and agentic risk

Overview

The skill appears to be a local knowledge-base helper that may edit personal note files, with no evidence of hidden network transfer or destructive behavior.

Install only if you are comfortable with the agent reading and editing the intended personal knowledge-base files. Keep backups or version control for those notes, and review any proposed edits before applying them.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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
Findings (1)

Lp3

Medium
Category
MCP Least Privilege
Confidence
95% confidence
Finding
The skill instructs the agent to read and modify files under `life/areas/**` via a bundled Python script, but it declares no explicit permissions. This creates a permission-model mismatch: an orchestrator or reviewer may treat the skill as lower risk than it really is, while the skill can still drive persistent file reads/writes to a sensitive knowledge base containing personal data.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal