diff --git a/.github/workflows/ci.yml b/.github/workflows/ci.yml
index 7d95d26..f50f4f8 100644
--- a/.github/workflows/ci.yml
+++ b/.github/workflows/ci.yml
@@ -47,11 +47,11 @@ jobs:
     # edge can't wedge the required context.)
     needs: changes
     # Every leg runs on GitHub-HOSTED runners now — the self-hosted NucBox Windows runners are RETIRED.
-    # The PRIVATE repo (wshallwshall) runs the UBUNTU leg only (its remaining Actions cost); the mirror
-    # (MEFORORG) runs the full ubuntu + windows-2022 + windows-2025 matrix, all FREE (hosted minutes are
-    # free on the public mirror). Hosted-everywhere is also safer: a self-hosted runner must never be
-    # reachable by a public repo (fork PR = RCE on the owner's LAN). `matrix.hosted` is the runner label
-    # set; the per-repo matrix (which drops the Windows legs on the private repo) is built in `changes`.
+    # This repo (MEFORORG) runs the full ubuntu + windows-2022 + windows-2025 matrix, all FREE (hosted
+    # minutes are free on a public repo); a FORK building its own pushes gets the UBUNTU leg only, to
+    # keep a contributor's personal CI cheap. Hosted-everywhere is also safer: a self-hosted runner must
+    # never be reachable by a public repo (fork PR = RCE on the owner's LAN). `matrix.hosted` is the
+    # runner label set; the per-repo matrix is built in `changes`.
     runs-on: ${{ matrix.hosted }}
     # Wall-clock backstop: bound each leg so a hung test fails in minutes, not the 6h default. Three
     # nested watchdogs catch a hang at increasing scope (#55): the pytest-timeout per-test cap (60s,
@@ -61,11 +61,11 @@ jobs:
     timeout-minutes: ${{ matrix.job_timeout }}
     strategy:
       fail-fast: false
-      # Per-repo matrix from the `changes` job: ubuntu-only on the private repo (Windows runners retired),
-      # full ubuntu+windows matrix on the mirror. Each leg carries os / python-version / hosted (the
-      # runner labels, an array) + the timeout knobs. NB: the Windows legs no longer EXIST on the private
-      # repo, so drop `test (windows-2022/2025, py3.14)` from wshallwshall's REQUIRED checks — a
-      # required-but-absent context blocks the PR forever.
+      # Per-repo matrix from the `changes` job: the full ubuntu+windows matrix here, ubuntu-only on a
+      # fork's own pushes. Each leg carries os / python-version / hosted (the runner labels, an array) +
+      # the timeout knobs. NB: a fork *PR* against this repo still runs in THIS repo's context, so it
+      # gets the full matrix — the required `test (windows-2022/2025, py3.14)` contexts are always
+      # present on a PR here, and a required-but-absent context (which blocks a PR forever) can't occur.
       matrix: ${{ fromJSON(needs.changes.outputs.matrix) }}
     defaults:
       run:
diff --git a/messagefoundry/scaffold.py b/messagefoundry/scaffold.py
index aad1c83..d2ead02 100644
--- a/messagefoundry/scaffold.py
+++ b/messagefoundry/scaffold.py
@@ -162,7 +162,7 @@ def archive(msg):  # type: ignore[no-untyped-def]
       - name: Verify SLSA build provenance before install
         env:
           GH_TOKEN: ${{ github.token }}
-        run: gh attestation verify dist-verify/messagefoundry-*.whl --repo wshallwshall/MessageFoundry
+        run: gh attestation verify dist-verify/messagefoundry-*.whl --repo MEFORORG/MessageFoundry
 
   check:
     needs: verify-engine
diff --git a/scripts/security/vuln_metrics.py b/scripts/security/vuln_metrics.py
index 80fbf4b..41cd94a 100644
--- a/scripts/security/vuln_metrics.py
+++ b/scripts/security/vuln_metrics.py
@@ -27,6 +27,7 @@
 import base64
 import csv
 import json
+import os
 import re
 import statistics
 import subprocess
@@ -264,7 +265,14 @@ def main(argv: list[str] | None = None) -> int:
     p = argparse.ArgumentParser(
         description=__doc__, formatter_class=argparse.RawDescriptionHelpFormatter
     )
-    p.add_argument("--repo", default="wshallwshall/MessageFoundry")
+    # Measure the repo the workflow actually runs in. vuln-metrics.yml invokes this with no --repo, so a
+    # hardcoded default silently decides what gets measured: it named the private vault, whose Dependabot
+    # PRs a public GITHUB_TOKEN cannot read — every KPI would have been computed over an empty window.
+    # $GITHUB_REPOSITORY makes it self-correcting; the literal is only for a local run outside Actions.
+    p.add_argument(
+        "--repo",
+        default=os.environ.get("GITHUB_REPOSITORY") or "MEFORORG/MessageFoundry",
+    )
     p.add_argument("--limit", type=int, default=200, help="Dependabot PRs to scan (the window)")
     p.add_argument("--timeout", type=float, default=20.0)
     p.add_argument("--csv", default="docs/security/metrics/vuln-metrics.csv")
diff --git a/tests/test_scaffold.py b/tests/test_scaffold.py
index 396a2dd..5270161 100644
--- a/tests/test_scaffold.py
+++ b/tests/test_scaffold.py
@@ -65,9 +65,13 @@ def test_scaffold_writes_the_skeleton(tmp_path: Path) -> None:
     # repo variable for indexes that strip attestations; the check job gates on it (never on verify failure)
     assert "verify-engine:" in ci
     assert (
-        "gh attestation verify dist-verify/messagefoundry-*.whl --repo wshallwshall/MessageFoundry"
+        "gh attestation verify dist-verify/messagefoundry-*.whl --repo MEFORORG/MessageFoundry"
         in ci
     )
+    # The scaffolded gate must name the repo that BUILDS the release — attestations are minted by the
+    # public repo's release workflow, so a private-vault slug here verifies against something no
+    # adopter can read. Pin the negative too: the retired slug must never creep back in.
+    assert "wshallwshall" not in ci
     assert "vars.MEFOR_VERIFY_ENGINE != 'off'" in ci
     assert "needs: verify-engine" in ci
     assert "needs.verify-engine.result != 'failure'" in ci