example-harness

Pass

Audited by Gen Agent Trust Hub on Aug 14, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill downloads a skill.toml file from the author's official GitHub repository at github.com/ruvnet/agent-harness-generator. This is used to configure the skill's execution environment.
  • [REMOTE_CODE_EXECUTION]: The skill uses npx to execute remote packages from the @metaharness NPM scope. These packages are the primary mechanism for scaffolding the different agent harnesses described in the documentation.
  • [COMMAND_EXECUTION]: The skill performs shell operations including directory creation (mkdir), file downloads (curl), and dependency installation (npm install) within the scaffolded project directory. These are routine operations for a developer tooling skill.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 14, 2026, 07:38 PM
Security Audit — agent-trust-hub — example-harness