Data Query Integrity
Security checks across malware telemetry and agentic risk
Overview
This is a documentation-only skill that makes API-based summaries check pagination and source data before reporting results.
This skill is appropriate if you want agents to be stricter when summarizing API data. Expect it to make agents perform extra pagination or narrower repeated queries and to disclose incomplete data instead of filling gaps by guesswork.
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.