Skip to main content

Code-completion proxy

The Guardian sits between the code-completion model and the IDE.

What it does

  • A model (GPT-4o, Claude, internal) returns a code suggestion.
  • The Guardian checks the suggestion for: live secrets, IMDS curls, license-incompatible patterns, prompt-injection in comments, dependency typosquats.
  • Passed suggestions reach the IDE unchanged. Corrected suggestions are patched (e.g. obvious secrets stripped). Blocked suggestions never appear in the editor.

Where Trinitite plugs in

SurfaceWhat governs it
Every code-completion callA code-suggestion-safety Guardian.
Per-developer attributionA nhi_dev_<username> identity tag on every call.
Forensic ledgerEvery suggestion (passed, corrected, blocked) writes a receipt — including which IDE.
Secret leak alertsA secrets-detected rule on the security stream → PagerDuty.
IMDS exfilL6 IMDS Shield catches it regardless of how the curl is constructed.

Concrete failure modes governed

  • Live API key in suggestion — see T-OUT-002.
  • curl 169.254.169.254 in a suggestion that gets accepted — see T-CLI-002.
  • License-incompatible verbatim copy — caught by a code-license-classifier sub-Guardian.

What's next

Skill Vault — provenance for the tools the agent uses.

Cookbook: SIEM export — wire the secret-detection events into your SIEM.