Security audit
AI Income Agent
Security checks across malware telemetry and agentic risk
Overview
The skill is only a markdown playbook with no hidden executable code, but it encourages autonomous public publishing and account-affecting income workflows without clear user approval boundaries.
Install only if you want an agent to help with monetization workflows, and keep manual approval over publishing, bounty submissions, affiliate posts, purchases, and payment/account checks. Do not paste real tokens into chat or shell history; use safer secret handling where available, and review anything public-facing before it is posted.
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.
Static analysis
No suspicious patterns detected.