llama-cpp

Pass

Audited by Gen Agent Trust Hub on Sep 17, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill provides instructions to download the project source code from the official llama.cpp GitHub repository and models from HuggingFace. These are well-known and trusted platforms in the AI development community.- [COMMAND_EXECUTION]: The documentation includes standard shell commands for building the project using make and executing inference via CLI tools like llama-cli and llama-server. These operations are consistent with the documented purpose of the software.- [SAFE]: No obfuscation, hidden instructions, credential exposure, or persistence mechanisms were detected. The skill accurately represents its functionality and follows standard development practices for documentation.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 17, 2026, 07:42 AM
Security Audit — agent-trust-hub — llama-cpp