broll-onboarding

Pass

Audited by Gen Agent Trust Hub on Aug 15, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill initiates local diagnostic and repair scripts (production-preflight.mjs and doctor.mjs). These executions are restricted to a defined 'safe-execution' reference and require explicit authorization for stateful repairs, minimizing the risk of unauthorized command execution.
  • [EXTERNAL_DOWNLOADS]: Mentions dependencies on specific libraries (remotion, hyperframes). The instructions contain a security-conscious rule against using npx for runtime checks, ensuring the agent relies on project-local, verified versions of these tools rather than potentially untrusted remote versions.
  • [SAFE]: The skill explicitly forbids sensitive operations like modifying shell profiles, altering global Node.js installations, or including private credentials/paths in output reports. This demonstrates a strong adherence to the principle of least privilege.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 15, 2026, 05:54 PM
Security Audit — agent-trust-hub — broll-onboarding