Security audit
Agent Designer Migrated
Security checks across malware telemetry and agentic risk
Overview
This appears to be a documentation-only agent-design skill with no bundled code that installs software, accesses private data, or runs in the background.
This skill is reasonable to install as documentation or workflow guidance. Before relying on its examples, separately review any referenced local skills such as subagente-optimizado, buscador_de_skills, or exa-search, because those components are not included here and would determine any real runtime 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.