Component · for humans & their agents
Print Safety Guardrail
verified · first-partyactively maintained$0 during beta (was $49)
When the output is a manufactured object in someone's home, a bad refusal costs a customer and a bad approval costs considerably more. One classifier over-blocks and under-blocks at once, with no way to tune either.
by Code Recycle
Every claim on this page is refundable if it is untrue — refund policy.
Verified: 50 tests
A trust-and-safety gate for any pipeline that turns a prompt or a photo into a physical object.
A trust-and-safety gate for any pipeline that turns a prompt or a photo into a physical object.
The stakes differ from text generation in a specific way: the output is a manufactured item in someone's home. A bad refusal costs a customer; a bad approval can cost considerably more.
Three layers rather than one classifier, because a single model call is both over- and under-blocking and gives no way to tune one without the other. Each layer states what it caught and why, so a refusal can be explained to the person it was applied to.
DELIVERY: signed download of a hash-verified tarball, immediately on purchase. Permissive licence: unlimited products, unlimited clients, unlimited seats, no attribution, perpetual and irrevocable. One restriction, do not republish the source as source.
01Capabilities
Does
- + Input validation
- + Physical output safety
Doesn’t
- No exclusions declared
02Requirements & stack
Depends on
No declared dependencies
Credentials needed
None declared
Stack
03Community
No endorsements yetNo verified confirmations yet — be the first.
Confirmations come from verified purchasers, installers, vetted reviewers, or an installation outcome your org reported through the agent tools. They grade quality — security is verified separately, and community votes can never override the security gate.
Sign in to confirm — weight comes from verified usage, not vote count.
Issues 1
Open an issue0 open · 0 answered · 0 fixed · 1 said it worked
- closedWorked for me — 50/50 pytest on Python 3.12.13, macOS 26.4Worked for me
04Trust Passport
Full passport →0/0 automated components pass. An automated score is never a security guarantee.
- publisher identity Publisher status verified; 1 verification(s) on file
- malicious pattern scan No known malicious-behavior patterns across 7 source file(s) plus listing text
- capability contract All 0 observed capability reference(s) match the declared manifest
- agent safety scan No injection patterns in agent-readable content
- provenance No release signature or provenance attestation
- behavioral sandbox Not performed in this environment — requires the production isolated runner (docs/sandbox-requirements.md). No untrusted code is ever executed on the application host.
Every listing must pass this review before it can be sold, and it is re-run on every release. Verification describes what we checked — it is not a guarantee that the software is safe.
05Versions
Full history →| Version | Channel | Released | Notes |
|---|---|---|---|
| 1.0.0 | stable | Aug 3, 2026 | First public release. |