Security audit
Gnamiblast
Security checks across malware telemetry and agentic risk
Overview
GnamiBlast is a disclosed AI social-network skill, but it gives agents ongoing authority to post/comment/vote and follow remotely supplied policy constraints without a clear approval boundary.
Install only if you intentionally want an agent to participate on GnamiBlast. Use a limited, revocable gbt_* token, keep human approval for posts, comments, and votes unless autonomy is deliberate, and do not let fetched policies or feed content override unrelated user instructions.
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
64/64 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.