@guardbee/mcp-prompt-injection-scanner

MCPattested
v0.2.11io.github.GuardBeeMITUpdated todaynpmGitHub

Scans RAG content/scraped pages for indirect prompt injection

Works in
ClaudeCursorCopilotGemini

Inferred from the transports this listing declares (stdio). A client not listed here hasn’t been ruled out — it just isn’t something Forge can confirm.

Attested build
A verified provenance attestation binds this artifact to the listed repository. Nobody has claimed the listing yet — this proves where the code was built, not who stands behind it.
497Downloads/wk
1GitHub stars
1Forks
todayLast update
Package
Authorio.github.GuardBee
LicenseMIT
Version0.2.11
Sourcenpm+mcp-registry
npm@guardbee/mcp-prompt-injection-scanner
GitHubGuardBee/guardbee-mcp
SBOMCycloneDX 1.6 ↓
Trust Status
A
85/100Trusted
✓Listed in Forge index+10/10
✓Identity verified · attested build+20/20
—Ed25519 publish signature+0/5
→ Included automatically when the publisher runs `forge publish`
—Domain verification+0/5
→ Publisher: host /.well-known/forge.json on the package homepage with { "publisher": "<github-login>" }
✓npm Trusted Publishing (Sigstore)+5/5
—npm maintainer match+0/5
→ Publisher: add the verified GitHub login to the npm package's maintainers (npm owner add <login>)
✓CVE scan · clean+30/30
✓Static analysis · clean+20/20
Paste into Claude Code, Cursor, or any AI assistant to fix all gaps
StatusIdentity verified
PublisherUnverified
SignatureUnsigned
Domain—
Provenance✓ Sigstore-verified · 9735ef2
Dependencies✓ 60 resolved+ · none vulnerable
Tool surface4 tools · none privileged
Security scan✓ Cleanv0.2.11 · todayHow well does this scan work?
EvalsNone
IndexedOct 9, 2026

Verification confirms publisher identity (repo ownership), not code safety. The security scan covers known CVEs and suspicious install scripts.

Tools

4 tools · none privileged
Statically extracted from the published packagev0.2.11 · 4h ago

Read out of the source npm actually ships, at scan time. The package was never executed. Tools registered dynamically at runtime, or hidden inside bundled or minified code, can be missed — so this is a floor on the tool surface, not a complete census of it.

scan_textScan a text string — a RAG chunk, a scraped web page, a document, a tool result — for indirect prompt injection payloads (instruction-override phrases, spoofed chat-template roles, hidden/invisible text, content addressing 'the AI' directly, data-exfiltration attempts) before it reaches a model's c…

Scan a text string — a RAG chunk, a scraped web page, a document, a tool result — for indirect prompt injection payloads (instruction-override phrases, spoofed chat-template roles, hidden/invisible text, content addressing 'the AI' directly, data-exfiltration attempts) before it reaches a model's c…

No input schema was published for this tool.

scan_fileScan a single file (a knowledge-base document, an HTML page, extracted text) for indirect prompt injection payloads

Scan a single file (a knowledge-base document, an HTML page, extracted text) for indirect prompt injection payloads

No input schema was published for this tool.

scan_directoryRecursively scan a directory — e.g. a RAG knowledge base or a corpus of scraped pages — for indirect prompt injection payloads. Automatically skips node_modules, .git, dist, and binary files.

Recursively scan a directory — e.g. a RAG knowledge base or a corpus of scraped pages — for indirect prompt injection payloads. Automatically skips node_modules, .git, dist, and binary files.

No input schema was published for this tool.

list_patternsList all indirect prompt injection patterns that the scanner can detect, grouped by category

List all indirect prompt injection patterns that the scanner can detect, grouped by category

No input schema was published for this tool.

4 of 4 tools published a description.

Tool names and descriptions are written by the publisher and shown verbatim as inert text. They are the strings an MCP client passes to a model, so Forge scans them for prompt-injection patterns — any finding appears with the security scan above. “Privileged” is a keyword match on the tool name, not an audit of what the tool does: a benign-sounding name can still do anything.

About

Scans RAG content/scraped pages for indirect prompt injection

Keywords
mcp
Alternatives
Comparing tool surfaces…

Tools exposed

4 tools · none privileged · observed by static extraction. A tool surface is what one scan read on one day, not a live capability list.

Linked names open Forge’s index of every entry observed exposing that tool. Browse all indexed tools.

Dependency tree

What one Forge scan resolved from npm metadata on 2026-10-10 — observed resolution, not a publisher declaration.

60 packages resolved · 4 direct · none carrying advisories Resolution stops at depth 4 and 60 packages.

The crawl stopped at the 60-package limit. The rest of the tree was never resolved.

36 more resolved packages are not drawn here (display cap: 24). Every dependency carrying an advisory is drawn regardless of the cap. Full inventory (CycloneDX SBOM)

Declared but not resolved

56 declared dependencies never landed in the tree. They are missing from Forge's resolution, not from the package.

+44 more not listed. The counts by reason above cover all of them.

Not followed: peerDependencies. This tree covers runtime dependencies only, so anything those pull in was never resolved.