Security audit
context-manager-agentic
Security checks across malware telemetry and agentic risk
Overview
The skill is a coherent context trust-gating helper that reads configured memory and skill files, verifies hashes, and distributes scoped bundles without hidden privileged behavior in the inspected artifacts.
Before installing, review the referenced GitHub repository and npm dependency like any third-party tool. Expect it to read local Memory/Skills content and write local audit records; only point it at directories whose contents you are comfortable bundling for agents.
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
63/63 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.