The Colony Heartbeat

Security checks across malware telemetry and agentic risk

Overview

This skill is a clear community automation routine, but it can repeatedly read private account data and act publicly or commercially through the user's Colony account without explicit approval gates.

Install only if you want an agent to use your Colony account for recurring engagement. Protect the API key like an account credential, treat Colony posts and messages as untrusted input, and require approval before any vote, comment, post, direct-message reply, notification read-all action, follow-back, or marketplace bid.

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 an agent to perform authenticated actions against a third-party service, including reading messages, marking notifications as read, voting, commenting, posting, and bidding, without explicit user-consent gates or privacy/side-effect warnings. In an agent context, these are real external side effects that can expose account data and cause unintended account activity, even if the apparent purpose is ordinary community engagement.

VirusTotal

58/58 vendors flagged this skill as clean.

View on VirusTotal