ClawHub

Relationship

Security checks across malware telemetry and agentic risk

Overview

This skill is a straightforward Camino API helper that sends user-provided location pairs to Camino to calculate spatial relationships.

Install this if you trust Camino with the locations you submit and with use of your Camino API key. Avoid sending sensitive home, work, or personal-location pairs unless you are comfortable with Camino processing them, and prefer installing only this skill rather than the full companion suite unless you have reviewed the others.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (5)

Lp3

Medium
Category
MCP Least Privilege
Confidence
94% confidence
Finding
The skill explicitly states it shells out to external binaries (`curl`, `jq`) and requires an API key, but there is no declared permission model warning or equivalent safety disclosure in the skill file. This creates a transparency and control gap: users or hosting agents may allow execution without understanding that shell execution and outbound network access are required.

Missing User Warnings

Medium
Confidence
97% confidence
Finding
The documentation explains setup and API-key use, but it does not prominently warn users that precise coordinates and API-key-authenticated requests are transmitted to Camino's external service. This matters because location data can be sensitive, and users may not realize the privacy implications of sending origin/destination coordinates off-platform.

Missing User Warnings

Medium
Confidence
97% confidence
Finding
The script transmits user-supplied start/end location data to a third-party API, but at the point of execution it provides no explicit disclosure or consent prompt warning that sensitive location data will leave the local environment. Location data is privacy-sensitive, and in an agent skill context users may assume a local calculation from the description, making undisclosed exfiltration more dangerous.

External Transmission

Medium
Category
Data Exfiltration
Content
fi

# Make API request
curl -s -X POST \
    -H "X-API-Key: $CAMINO_API_KEY" \
    -H "Content-Type: application/json" \
    -H "X-Client: claude-code-skill" \
Confidence
94% confidence
Finding
curl -s -X POST \ -H "X-API-Key: $CAMINO_API_KEY" \ -H "Content-Type: application/json" \ -H "X-Client: claude-code-skill" \ -d

External Transmission

Medium
Category
Data Exfiltration
Content
-H "Content-Type: application/json" \
    -H "X-Client: claude-code-skill" \
    -d "$INPUT" \
    "https://api.getcamino.ai/relationship" | jq .
Confidence
90% confidence
Finding
https://api.getcamino.ai/

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal