Security audit
Launch Feedback Synthesizer
Security checks across malware telemetry and agentic risk
Overview
This skill is a coherent launch-feedback workflow that reads user-provided feedback, summarizes it, and only saves results with user confirmation.
Before installing, be aware that the skill may process launch comments, store reviews, support tickets, and feedback-board exports. Only confirm saving if you are comfortable storing those summaries in memory, and separately verify platform review policies before acting on any testimonial or review-harvest plan.
SkillSpector
By NVIDIA
Vulnerability Patterns
- 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
- Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
VirusTotal
61/61 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.