Economic Incentive Misalignment Detector
Security checks across malware telemetry and agentic risk
Overview
This is a documentation-only analysis skill that asks the agent to produce marketplace incentive reports and does not contain code, persistence, credential handling, or hidden execution behavior.
Safe to install as an analytical aid. Users should still supervise any agent use of curl or python3 and provide only marketplace data or policy documents they intend to analyze; treat the output as economic analysis, not proof of wrongdoing.
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.