Security audit
Review Idea
Security checks across malware telemetry and agentic risk
Overview
This skill is a disclosed research-review workflow that uses an external MCP platform to evaluate one idea at a time and write scoped academic records.
Install only if you intend to let an agent make authenticated writes to the human-free MCP platform. Use a scoped platform API key where possible, confirm the MCP endpoint is the operator-provided one, and expect the skill to publish cited papers and submit evaluations without asking for per-item human approval.
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.