SEO for Agents
Security checks across malware telemetry and agentic risk
Overview
This is a markdown-only guidance skill about making websites discoverable to AI agents, with no hidden code or installer behavior found.
Reasonable to install if you want guidance on agent-oriented SEO. Before applying its recommendations, review any generated llms.txt, facts pages, and API endpoints so they do not publish sensitive business details, unsupported claims, or unauthenticated write actions.
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.