Mercado Libre

Security checks across malware telemetry and agentic risk

Overview

The skill appears to be a Mercado Libre helper with a broad activation note, but the supplied evidence does not show hidden, destructive, or unrelated behavior.

Install only if you want Mercado Libre-related assistance. Before letting it act on seller/account data, confirm what actions it can perform and require explicit approval for listing, order, pricing, or account changes.

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: 93% confidence
Finding: The setup allows the skill to be 'always on for Mercado Libre requests' but does not define explicit trigger boundaries, scope, or disambiguation rules. This can cause the agent to activate on loosely related commerce or marketplace queries, increasing the chance of unintended behavior, inappropriate persistence of context, or execution of Mercado Libre-specific workflows when the user did not clearly request them.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal