Dynamic code execution detected.
Critical
- Code
- suspicious.dynamic_code_execution
- Location
- tests/test_modelpilot_report.py:19
Security audit
Ollama Model Pilot
Security checks across malware telemetry and agentic risk
Overview
This skill is a local Ollama benchmarking helper, and its files align with that purpose without hidden upload, credential, persistence, or destructive behavior.
This appears safe to install for local Ollama model evaluation. Before running benchmarks, use fictional or explicitly approved prompt files, review output paths because reports may store prompts and model responses locally, and approve any model download or deletion separately.
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
Detected: suspicious.dynamic_code_execution