Security audit
Blocker Minimum Input
Security checks across malware telemetry and agentic risk
Overview
This skill only teaches agents to report blockers clearly and includes basic privacy guidance for redacting secrets.
Reasonable to install for clearer blocker reports. Review blocker reports before sharing them externally, because exact error messages can still reveal sensitive project names, paths, or account details even when credentials are redacted.
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.
Static analysis
No suspicious patterns detected.