Adverse Event Narrative
Security checks across malware telemetry and agentic risk
Overview
This skill is a local drafting aid for adverse-event reports, with no evidence of hidden network access, credential use, persistence, or destructive behavior.
Use this only as a drafting and formatting aid. Work with de-identified case data where possible, keep file paths scoped to the intended case files, and require qualified pharmacovigilance or medical review before using any narrative or causality language for regulatory submission.
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
62/62 vendors flagged this skill as clean.
