1 findingStatic scanned
Lets your AI assistant audit a domain's DNS, SPF, DMARC and DKIM records and flag dangling subdomains.
1.5k installs/moMIT
MCP Prompt Injection Scanner
guardbee · MCP server
MCP Prompt Injection Scanner checks content, rather than code, for indirect prompt injection: instructions planted in a retrieved document, scraped web page or RAG chunk that a model would later read. It looks for override phrases, spoofed system roles, invisible text, text addressed to the AI and instructions to send data to an outside URL, in English and Turkish. It can scan text, a file or a directory, and run from a command line with SARIF output for CI. It sends usage telemetry by default, which can be turned off.
Written by ooruby from the README of @guardbee/mcp-prompt-injection-scanner 0.2.11.
Not claimed by its maker. Is this yours? Prove it and answer the findings
Why it's useful
Instructions planted in documents and web pages can reach a model through retrieval, and this flags them so you can review them first.
What you could do with it
- Scan a scraped web page for hidden or instruction-like text before your agent reads it.
- Scan a whole knowledge-base folder for planted instructions and get a list of findings.
- Scan a knowledge-base repository on every pull request and write the results as SARIF.
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
- Licence and provenance
- finding
- no LICENCE file at the root (.)
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.
Receipt history: every signed receipt for every version of this listing, and what changed between them.
In its maker's words
MCP server that scans documents, scraped pages, and RAG content for indirect prompt injection payloads — instruction-override phrases, spoofed chat-template roles, hidden/invisible text, content addressing the AI directly, and data-exfiltration attempts
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 0.2.11, the file with digest sha512-7erMwsZuIjmkihNNihaVdmeGx7NthLeea+cqiKs2XBfTIgUe9dM9C/jMPXRE00rGmu6Dah18KZKrn6+IWpcptQ==, 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
Paste this into your client's MCP configuration.
{
"mcpServers": {
"guardbee-prompt-injection-scanner": {
"command": "npx",
"args": [
"-y",
"@guardbee/mcp-prompt-injection-scanner@0.2.11"
]
}
}
}Or run it directly.
npx -y @guardbee/mcp-prompt-injection-scanner@0.2.11Pinned to 0.2.11, 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
- @guardbee/mcp-prompt-injection-scanner
- Version read
- 0.2.11
- Resolved
- 2026-10-10
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/guardbee/guardbee-mcp
- Commit
- 9735ef29a3ce
- 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/guardbee-mcp-prompt-injection-scanner)About this listing
- Kind
- MCP server
- Category
- Developer tools
- Pricing
- Free
- Sandbox
- No
- Hosted
- No
- Updated
- 2026-10-09
More from guardbee
See the storefrontSimilar MCP servers
All MCP servers2 findingsStatic scanned
Adds Storybook component and story documentation tools to an MCP server you run yourself.
9.4M installs/moMIT
Clean scanStatic scanned
Lets your agent control and inspect a live Chrome browser using Chrome DevTools.
9.9M installs/moApache-2.0
Clean scanStatic scanned
Pulls version-specific library docs and code examples straight into your agent's context.
3.9M 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.