4 findingsStatic scanned
Lets your agent scan AI app and agent code for security risks before you commit, merge or deploy.
No reviews yetMIT
Llmverify
kingcaliber · App
Llmverify is a Node.js toolkit that sits between your LLM and your users. It checks user input for prompt injection and jailbreak attempts, gives model output a risk level from hallucination and consistency checks, detects and masks personal data such as emails, phone numbers and card numbers, and repairs broken JSON. It can also wrap an LLM client to track latency and behaviour changes. Its checks are deterministic, run locally without model calls on the free tier, and list in each result what was not checked.
Written by ooruby from the README of llmverify 1.8.0.
Not claimed by its maker. Is this yours? Prove it and answer the findings
Why it's useful
You can add checks for injected instructions, leaked personal data and broken JSON to an LLM feature without sending data to another model.
What you could do with it
- Mask emails, phone numbers and API keys in a model's reply before showing it to a user.
- Screen each user message for prompt injection before it is sent to your model.
- Repair a model's broken JSON output before your parser reads it.
Written from its documentation: what it says it can do, not what our checks found.
Maintenance
Not measuredNo release date is on record for this package yet. The nightly publisher check records one as it reaches each npm package, about once every ten nights.
Release activity only: it says nothing about quality or safety, and a finished small package can be fine without releases. How it is measured
- Command execution is bounded
- inventory
- node child_process (package.json:44)
- An inventory of where the code starts another program, not a verdict on this row: whether each one runs a fixed program or whatever it is handed takes a reading by hand.
Published because it was found. A finding is information about where the limits are, not a verdict that the software is unsafe.
What this does not cover
- Everything. Treat it as you would software from anywhere else.
Corrected after a reading by hand on 2026-10-10
- No shipped credentials: the automated note “The scan matched 2 credential-shaped strings in the published files. Location withheld pending disclosure to the maker.” was withdrawn. Sample values in an example of its personal data detection, among them the example key from AWS's own documentation.
Receipt history: every signed receipt for every version of this listing, and what changed between them.
In its maker's words
AI Output Verification Toolkit — Local-first LLM safety, hallucination risk signals, PII redaction, prompt injection defense, and runtime monitoring. Zero telemetry. OWASP LLM Top 10 aligned.
Compare with
Compare all 4How far this has been checked
Static scanned
- What it establishes
- Its published package, or for a hosted server its source repository at a recorded commit, was read file by file, without running it, by every check in our current scan.
- What it does not
- How it behaves when it runs, or anything the scan does not read yet: several rubric checks, the repository's history, and compiled code in folders named dist or build. For a hosted server, that the endpoint runs the code that was read. The ooruby Index sets out exactly what was read.
- Exactly what was read
- Version 1.8.0, the file with digest sha512-XLUF9Aeqh7fD6FebyvOAj1OXq4zc/63J2o4xEvhsElKAQCClKVdw4hLDDlSLY28zyJpQBpXXyz4Smv+gLoKCJA==, as the registry publishes it. A published version cannot be replaced, so this names the same bytes for anyone who checks.
- Authentication
- Runs locally. No hosted endpoint is listed for this package. You run it on your own machine, so there is no endpoint of ours to authenticate against.
Adding it
Run it with:
npx -y -p llmverify@1.8.0 llmverifyPinned to 1.8.0, which is the version the findings above were found in. Drop the version to take whatever is newest, and the report on this page stops describing what you installed.
Where this came from
- Registry
- npm
- Package
- llmverify
- Version read
- 1.8.0
- Resolved
- 2026-10-09
Built from source, attested
npm publishes a signed statement that this exact package was built from the repository below, at this commit. It is verifiable without taking our word for it.
- Repository
- github.com/subodhkc/llmverify-npm
- Commit
- f796fdeba548
- Built by
- github.com/actions/runner/github-hosted
- Registry publish attestation
- signed by npm · 2026-10-10
- Checked
- 2026-10-10
The badge, if this is your listing
It renders the current rung (static scanned) and links back here, where what that does and does not establish is one click away. It updates itself as the evidence deepens.
[](https://ooruby.com/market/llmverify)About this listing
- Kind
- App
- Category
- Developer tools
- Pricing
- Free
- Sandbox
- No
- Hosted
- No
- Updated
- 2026-10-09
More from kingcaliber
See the storefrontSimilar apps
All apps4 findingsStatic scanned
Puts Claude in your terminal to understand your codebase, edit files and handle git workflows.
80.2M installs/moSEE LICENSE IN README.md
2 findingsStatic scanned
Gives your app one API for streaming from many AI model providers, with typed and validated tools.
14.6M installs/moMIT
1 findingStatic scanned
Estimates how many tokens a text will use without loading a full tokeniser, from code or the shell.
5.8M installs/moMIT
Verification records what our published tests found on a specific version at a specific date. It is not a warranty, and it does not certify that software is free of defects.