ClawHub

Graphiti

Security checks across malware telemetry and agentic risk

Overview

This skill transparently lets an agent search and add memories in 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, prefer Clawdbot config because the documented GRAPHITI_URL fallback is not actually honored by the helper script, and avoid storing secrets or untrusted content as memories.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (5)

Lp3

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding
Without declared permissions the skill's intent is opaque and cannot be validated.

Tp4

High
Category
MCP Tool Poisoning
Confidence
95% confidence
Finding
This is a mismatch because the declared description promises knowledge graph operations such as searching facts, adding episodes, and extracting entities/relationships, but the provided code does none of those things. Instead, it acts as an environment discovery and service-availability check utility. While a health check could be a supporting utility, it is the entirety of the code shown, so the actual implemented behavior materially differs from the declared primary purpose.

External Transmission

Medium
Category
Data Exfiltration
Content
```bash
bash command:"
GRAPHITI_URL=\$({baseDir}/references/env-check.sh)
curl -s -X POST \"\$GRAPHITI_URL/facts/search\" \
  -H 'Content-Type: application/json' \
  -d '{\"query\": \"YOUR_QUERY\", \"max_facts\": 10}' | jq .
"
Confidence
60% confidence
Finding
curl -s -X POST \"\$GRAPHITI_URL/facts/search\" \ -H 'Content-Type: application/json' \ -d

External Transmission

Medium
Category
Data Exfiltration
Content
```bash
bash command:"
GRAPHITI_URL=\$({baseDir}/references/env-check.sh)
curl -s -X POST \"\$GRAPHITI_URL/messages\" \
  -H 'Content-Type: application/json' \
  -d '{\"name\": \"EPISODE_NAME\", \"content\": \"EPISODE_CONTENT\"}' | jq .
"
Confidence
60% confidence
Finding
curl -s -X POST \"\$GRAPHITI_URL/messages\" \ -H 'Content-Type: application/json' \ -d

External Transmission

Medium
Category
Data Exfiltration
Content
```bash
bash command:"
GRAPHITI_URL=\$({baseDir}/references/env-check.sh)
curl -s -X POST \"\$GRAPHITI_URL/facts/search\" \
  -H 'Content-Type: application/json' \
  -d '{\"query\": \"Tell me about Essam Masoudy\", \"max_facts\": 5}'
"
Confidence
60% confidence
Finding
curl -s -X POST \"\$GRAPHITI_URL/facts/search\" \ -H 'Content-Type: application/json' \ -d '{\"query\": \"Tell me about Essam Masoudy\", \"max_facts\": 5}' " ``` Add a memory: ```bash bash comman

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal