ClawHub
Back to skill

Security audit

Graphiti

Security checks across malware telemetry and agentic risk

Overview

This skill transparently lets an agent search and add entries to a Graphiti knowledge graph, with no hidden or malicious behavior found.

Install this only if you want the agent to query and add persistent entries to your Graphiti knowledge graph. Verify the Graphiti endpoint before use, and avoid storing secrets or untrusted content as memories.

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 (2)

Lp3

Medium
Category
MCP Least Privilege
Confidence
92% confidence
Finding
The skill exposes shell execution behavior via embedded bash commands but does not declare corresponding permissions or capability requirements. This creates a trust and review gap: operators may believe the skill is documentation-only or lower risk, while it can invoke local scripts and make outbound network requests through the shell.

Missing User Warnings

Medium
Confidence
89% confidence
Finding
The skill documents unaudited write operations to the knowledge graph API without warning that these actions persist or mutate stored data. In practice, a user or agent could add incorrect, sensitive, or malicious content to the graph, causing durable data poisoning, privacy issues, or downstream decision errors.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.