Ai Discoverability Audit
Security checks across malware telemetry and agentic risk
Overview
This is an instruction-only marketing audit skill that asks the agent to run brand-related AI search queries and produce recommendations, with no code execution or hidden access requests.
Safe to install as an instruction-only audit template. Use public or non-sensitive brand information when running its queries on external AI platforms, and remove the author's booking link from generated output if you do not want promotional material included.
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.