Security audit
Agent Summary
Security checks across malware telemetry and agentic risk
Overview
This is a simple progress-summary skill that reads recent subagent status messages for its stated purpose and does not install or run code.
Install this only if you are comfortable with the agent reading recent subagent messages to summarize progress. Avoid using it for tasks where subagent conversations may contain secrets, regulated data, or private content that should not be surfaced in status updates.
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.
Static analysis
No suspicious patterns detected.