Plot Logic Pipeline
Security checks across malware telemetry and agentic risk
Overview
This skill is a markdown-only guide for analyzing scientific papers and does not request privileged access, credentials, code execution, persistence, or network activity.
This appears safe to install for structured scientific-paper review. Users should still verify the agent's scientific conclusions and evidence-strength judgments, because the main residual risk is analytical accuracy rather than security.
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
63/63 vendors flagged this skill as clean.