Security audit
靶点药物证据评估（Target-Drug Evidence Evaluation）
Security checks across malware telemetry and agentic risk
Overview
This skill is a structured pharmaceutical evidence-evaluation workflow with disclosed external data lookups and no executable code or persistence.
Before installing, users should be comfortable with target, indication, and patent-related queries being sent to the configured Patsnap/pharma intelligence MCP services. The skill is suitable for evidence triage, but its own guardrails correctly state that outputs should not be treated as legal, investment, or clinical decision 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
61/61 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.