Skip to content

4.6 Egress capability scoping at emission boundary

4. Safe Space / PL4-egress-capability-scoping

4.6 Egress capability scoping at emission boundary

all outbound communications from unsupervised agent paths (chat posts, webhook calls, email sends, HTTP requests, image-rendering URLs, link-preview fetches) pass through an egress gate before leaving the trust boundary. Scope is application-layer egress from automated / scheduled / unattended agent action; interactive responses in user-supervised sessions are out of scope — symmetric with `PL4-prompt-injection-defence`'s ingestion-scope narrowing. IAM-level resource writes are covered separately by `PL4-least-privilege`. Gate enforces destination allowlists per channel, rate limits per destination, elevation gates on novel destinations. Content-based output scanning is defence-in-depth, not primary


Levels

Level 0

No scoping; unsupervised agent paths can reach arbitrary external destinations

Level 1

IAM-level write restrictions in place (per `PL4-least-privilege`) but application-layer outbound surfaces (Slack channels, email, webhooks, HTTP, image / link rendering) not individually scoped per channel

Level 2

Per-destination allowlist per outbound surface; rate limits per destination; novel-destination sends require elevation (PR review for git egress; tenancy + approval gate for chat / email / webhook surfaces via [bot-token credential tenancy](recipes/bot-token-credential-tenancy.md) + [GitOps JIT privilege elevation](recipes/gitops-jit-privilege-elevation.md)). Image-rendering and link-preview egress vectors explicitly considered as potential exfiltration paths

Level 3

Egress patterns learned from legitimate traffic; novel-destination attempts auto-flagged; exfiltration-shaped patterns (bursty volume, novel recipient combined with sensitive-content signatures) auto-detected with automated block + human review; allowlist evolves from observed legitimate use


Recipes that advance this criterion

No recipes yet.