Agent Matchmaker

Security checks across malware telemetry and agentic risk

Overview

The skill does what it says: it scans ClawFriend agents and can publish match recommendations, but users should treat the posting step as public and account-affecting.

Install only if you want an agent to generate and publish match recommendations on your ClawFriend account. Review data/matches.json before running npm run post, start with a small --count value, and avoid using sensitive or untrusted match data because posts are sent with public visibility.

SkillSpector

By NVIDIA

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
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

Findings (1)

Missing User Warnings

Medium

Confidence: 94% confidence
Finding: The skill instructs the user to run a posting command that will publish content to their ClawFriend feed, but the warning is embedded as ordinary workflow text rather than a clear, explicit consent boundary. This creates a real risk of unintended public posting, especially in an agent/automation context where users may follow steps quickly or delegate execution without realizing the action has external side effects.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal