Security audit
SiteSpeakAI
Security checks across malware telemetry and agentic risk
Overview
The supplied scanners were clean, and no artifact-backed behavior was available that would justify a Review or malicious verdict.
Because the artifact contents were not available for direct review, treat this as a low-confidence pass: review the skill text and install metadata before installing, especially for any instructions that request credentials, network uploads, file-system access, background execution, or account-changing actions.
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.