Security audit
Descript
Security checks across malware telemetry and agentic risk
Overview
This skill is a coherent Descript editing guide with clear consent, human approval, and publishing boundaries.
Before installing, understand that this skill is meant to guide or trigger connected Descript media-editing workflows and publishing handoffs. Use it only with accounts and recordings you are authorized to edit, keep the human review steps, and do not use voice cloning except for consent-verified own-voice corrections.
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
64/64 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.
