Security audit
X Algo Claim Reviewer
Security checks across malware telemetry and agentic risk
Overview
This is a low-risk instruction-only skill for checking public X algorithm claims against public evidence.
Reasonable to install for public-source claim review. Users should avoid giving it private account data, authenticated pages, or session access, and should treat its output as an evidence review rather than proof of how X's live production ranking system behaves.
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
65/65 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.