Security audit
Check Sources
Security checks across malware telemetry and agentic risk
Overview
This skill checks connected health-data sources and record counts, with no evidence of hidden code, export behavior, or unsafe automatic actions.
Install only in environments where the HealthClaw/FHIR tools and STEP_UP_SECRET are trusted, because even source connection status, last activity, and record counts can reveal sensitive health information.
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.