Security audit
target-discovery
Security checks across malware telemetry and agentic risk
Overview
This skill is a disclosed life-science analysis workflow that uses external PatSnap/OpenClaw tools for compound target discovery and patent risk checks, with no hidden code or persistence found.
Before installing, users should be comfortable sending confidential compound SMILES and research questions to the configured PatSnap/OpenClaw MCP services. Treat FTO, target, medical, and patent outputs as research support requiring expert verification, not as legal or clinical advice.
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.