Halaman ini diterjemahkan oleh mesin. Baca versi asli dalam bahasa Inggris.

Feature

core/prompt-deny-patterns

Refuses a model request whose text matches one of the regular expressions the attachment lists, before the request reaches a model. It acts at the gateway hop: it attaches to a component standing in the request path that declares it can match the model payload it routes against a list of patterns (dataplane.aggrega.ai/prompt-guard: pattern-list), and that component turns a matching request away instead of forwarding it. The control is a literal match and is only as good as its list: it refuses text an expression matches, and it does not catch a paraphrase, the same request in another language, text disguised by an encoding, text split across messages, tool-call arguments, images or anything in the model's reply. A request that does not pass through the gateway is not seen at all. Attaching it therefore does not establish that a payload can be trusted and does not stop prompt injection; judging whether a request tries to override the instructions a model was given is a different control, declared as core/prompt-injection-shield. Which messages a gateway reads, whether letter case counts, and what a refused caller receives are the gateway's, and each realization states them for its own.

Asal-usul

ResmiDitandatangani oleh identitas penandatangan yang diakui katalog ini sebagai penerbit resmi.
Digest konten
sha256:aae6b775b5c8c67cd03ffe7a13f315d1e546ff4c883da6ba4a40371349828ea0
Dipublikasikan
2026-11-10T10:17:17Z
Identitas penandatangan
https://token.actions.githubusercontent.com/https://github.com/aggrega-ai/aggrega-hub/.github/workflows/catalog-publish-sign.yml@refs/heads/main

Tanda tangan

  • Resmiapplication/vnd.dev.sigstore.bundle.v0.3+json

    https://token.actions.githubusercontent.com/https://github.com/aggrega-ai/aggrega-hub/.github/workflows/catalog-publish-sign.yml@refs/heads/main

    sha256:863f110be03a75657ab2a6a35b357c411838ccc979ec8bd198a4a8ab96cd1389

Referensi pada versi ini

oci://hub.aggrega.ai/feature/core/prompt-deny-patterns:1.0.0
Berlaku untuk
dataplane.aggrega.ai/prompt-guard=pattern-list
Berkonflik dengan
—

Parameter pengembang

Nilai yang ditetapkan pengembang saat melampirkan fitur ini.

Memperluas BaseComponents#/schemas/BaseFeatureParameter

NamaTipeBawaanWajibDeskripsi
deny_patternsarray (min 1)—yaThe regular expressions a request's text is matched against; a request any one of them matches is refused. Each is handed to the gateway exactly as written, in the expression syntax that gateway reads, and the build does not check that an expression is valid. At least one is required, and none may be empty, because an empty expression matches every request.
allow_patternsarray—tidakExpressions a request must match at least one of to be forwarded at all, checked beside deny_patterns. Only a gateway whose pattern guard also admits by pattern can honour it; a realization for a gateway without such a list refuses an attachment that sets it, naming the capability the gateway declares, rather than forwarding requests the list would have turned away.

Kontrak keluaran

Nilai yang dipublikasikan fitur ini kepada konsumen.

Tidak ada nilai keluaran yang dideklarasikan.

Anotasi

Tidak ada anotasi yang dideklarasikan.

Relasi

Sisi bertipe ke dan dari entitas lain yang dipublikasikan. Referensi tanpa target yang dipublikasikan ditampilkan sebagai sisi yang terputus, bukan sebagai tautan.

Menggunakan

Digunakan oleh

Referensi konsep Feature →

Katalog Aggrega — indeks terbuka berisi komponen, fitur, resep, dan plugin yang merendernya.

Dibangun dengan sistem desain Aggrega yang digunakan bersama.

Privasi