Evidence-First Research
Security checks across malware telemetry and agentic risk
Overview
This is a research-guidance skill that tells the agent to check evidence before scientific or medical work, without installing code or requesting credentials.
Reasonable to install for research planning and evidence review. Use it as support for evaluating sources, not as a substitute for clinical judgment, and avoid giving an agent patient-identifiable information or sensitive private research files unless that sharing is intended and appropriately controlled.
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
66/66 vendors flagged this skill as clean.