Open Models Almanac
Methodsinference & servingagentic scaffolding

single mention · inference & serving

Egress allowlist and prompt hardening

Training-time hardening of egress allowlists and system prompts to reduce model exploits.

The sources on this page only mention it in passing. The line above is the extraction's one-line gloss. See agentic scaffolding for the methods filed beside it.

Filed under inference & serving › agentic scaffolding