AGENT LAB: SKILLS

grepai-embeddings-ollama

Fail

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: HIGHREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [REMOTE_CODE_EXECUTION] (HIGH): The skill instructs users to install software using curl -fsSL https://ollama.com/install.sh | sh. This pattern execution of a remote script directly in the shell without verification is a high-severity security risk. Although it is the primary setup method for the tool, the source is not in the trusted repository list.
  • [COMMAND_EXECUTION] (HIGH): The skill includes instructions to use sudo systemctl to enable and start services, which requires administrative privileges and modifies system persistence.
  • [EXTERNAL_DOWNLOADS] (LOW): The skill facilitates the download of software and models from ollama.com. Because this is central to the skill's function, the severity is lowered, but the source remains unverified per the defined trusted organizations list.
Recommendations
  • HIGH: Downloads and executes remote code from: https://ollama.com/install.sh - DO NOT USE without thorough review
  • AI detected serious security threats
Audit Metadata
Risk Level
HIGH
Analyzed
Feb 17, 2026, 04:58 PM