Project Writing
Security checks across malware telemetry and agentic risk
Overview
This skill only changes response formatting for project-writing output and does not request access to files, tools, accounts, or background execution.
This is reasonable to install if you want project-writing responses wrapped in ama-doc tags. Expect formatting changes when the skill is active, but the reviewed artifact does not show file access, account access, command execution, persistence, or data-sharing behavior.
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
65/65 vendors flagged this skill as clean.