Security audit
learning-aggregator
Security checks across malware telemetry and agentic risk
Overview
This skill is a disclosed, read-only learning report generator, with optional deeper trace review that users should invoke only when they are comfortable analyzing session transcripts.
Install this if you want an agent to summarize local learning logs into recurring-pattern reports. Use `--deep` only when you are comfortable letting the agent inspect session transcripts, since they can contain sensitive project context and user prompts.
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
66/66 vendors flagged this skill as clean.