sync-trending

Security checks across malware telemetry and agentic risk

Overview

The skill is transparent about its goal, but its verification mode can install and run unfamiliar third-party repository code with limited containment.

Install only if you are comfortable with a skill that may ask to clone and run unfamiliar repositories. Use it for trend reports freely, but approve verification only in a disposable container or VM, review each install and run command first, and avoid using it in a workspace or shell environment that contains secrets.

SkillSpector

By NVIDIA

Vulnerability Patterns

Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (1)

Vague Triggers

Medium

Confidence: 86% confidence
Finding: The skill description is broad enough to trigger on common requests about tools, updates, or project ideas, which can activate a workflow that fetches external content, reads local project files, and may later lead to cloning and executing third-party code. Broad invocation increases the chance of the skill being used in contexts where the user did not intend such expansive behavior, raising the risk of unnecessary data exposure and unsafe follow-on actions.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal