Security audit
AANA Research Grounding Skill
Security checks across malware telemetry and agentic risk
Overview
This is a non-executable research-grounding instruction skill that tells agents to stay within allowed sources and avoid unsupported citations.
Install this if you want agents to be stricter about citations and source-bounded research. If you connect an external checker, configure it yourself and keep using the skill's redaction rules so private records, secrets, and full source text are not sent unnecessarily.
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
62/62 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.