OnePerson

Security checks across malware telemetry and agentic risk

Overview

This is a small, disclosed integration for the 1Person service that requires an API key and advertises autonomous workflows and persistent memory, with no code or hidden execution behavior in the artifact.

Install this only if you intend to use the 1Person external service. Use a dedicated or least-privileged API key if available, keep ONEPERSON_API_KEY out of shared environments, and review 1Person's workflow approval, connected-tool permissions, and memory retention settings before using it with sensitive data or high-impact accounts.

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: 81% confidence
Finding: The skill requires an API key for an external service but does not warn users that data may be sent to a third party or explain how credentials are handled. In an agent environment, this can lead to users supplying secrets without informed consent and may expose sensitive prompts, task data, or workflow context to the external platform.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal