Mac Multi-Instance Deployment

Security checks across malware telemetry and agentic risk

Overview

This is a coherent Convex performance-audit skill that may inspect and suggest edits to a project, but its behavior is disclosed and aligned with its purpose.

Install if you want Convex-specific performance guidance. Before allowing it to run commands or make larger schema/data-model changes, review the proposed plan, especially any npx command, migration, digest table, index rollout, or cross-cutting performance refactor.

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: 90% confidence
Finding: The skill enables implicit invocation, but the trigger description is broad and generic rather than narrowly scoped. This can cause the agent to auto-select the skill in contexts the user did not explicitly intend, which increases the chance of unintended file changes, configuration actions, or boundary updates being performed under an overly permissive match.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal