gemma-2-2b
A base model — Vulcora reads a model by differencing it against the parent it was derived from, and a base model is the root of that tree, with no parent. The question is category-inapplicable, so there is no verdict: not a pass and not a fail.
◆ Vulcora reads a model against its parent — and a base model has no parent to read against. Nothing to compare, so there is no verdict to give: not applicable, not a clean bill of health
Vulcora reads the weights- modelauditpromptfooserialization exploit
reads manifests, configs, embedded templates & safetensors
heuristic auditing of a model repo for suspicious files, chat-template SSTI, non-allowlisted pickle globals, and license/provenance smells; a broad repo linter, not a weight-tampering detector.
artifact-only here: README/prose withheld (see policy)
- model-signingOpenSSF / Sigstoreprovenance
reads Sigstore signature bundles
verifying a cryptographic provenance signature over model files; it can only attest what a publisher signed.
requires a published Sigstore bundle; no scanned model ships one
The 3 tools run here found nothing of the kind they read — this model doesn’t ship that kind of file. That is not a clearance. A base model has no parent to read against — no verdict was given, and that is not a clean bill of health.
Think this verdict is wrong?
Signed-in users can formally refute a read — Vulcora re-reads the model against your claim and records the outcome. You'll need an account to file one.
Refutations are actor-gated — a guest can't file one.
Want a verdict you can prove — on your own model?