ort-build

Pass

Audited by Gen Agent Trust Hub on May 15, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • Command Execution: The skill instructs the agent to execute build scripts such as build.sh, build.bat, and build.py. This is the intended purpose of the skill, facilitating the compilation of source code into executable libraries.
  • Indirect Prompt Injection Surface: The skill supports loading configuration from external files using the @ prefix (e.g., @custom_options.opt). This is a common pattern in build systems, though it represents an entry point where the agent might ingest data from the local environment.
  • Ingestion points: Configuration files and build logs.
  • Boundary markers: Not explicitly defined in the provided instructions.
  • Capability inventory: Subprocess execution for build and test phases.
  • Sanitization: Standard build script processing logic.
Audit Metadata
Risk Level
SAFE
Analyzed
May 15, 2026, 01:51 PM
Security Audit — agent-trust-hub — ort-build