Security audit
Awesome AI Sources
Security checks across malware telemetry and agentic risk
Overview
This skill is a straightforward public RSS feed reader for AI-related sources, with no evidence of hidden data access or unsafe behavior.
Install this if you are comfortable with your agent making outbound requests to www.agenticbrew.ai and displaying external feed links. Review any proposed daily or weekly schedule before enabling it, and treat feed content as untrusted external information rather than instructions for the agent to follow.
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.