# @guardbee/mcp-prompt-leak-scanner

Catches leaked credentials and PII in outbound LLM prompts

- **Type:** MCP server
- **Trust:** 65/100 (B), scored on the package rubric
- **Verification:** verified (build provenance)
- **Version:** 0.1.15
- **Author:** io.github.GuardBee
- **License:** MIT
- **npm:** @guardbee/mcp-prompt-leak-scanner
- **Source:** https://github.com/GuardBee/guardbee-mcp
- **Compatible clients:** claude-code, cursor, copilot, gemini (basis: transport)

## Trust

65/100 (B), scored on the package rubric
- Publisher verified: no
- Build provenance: verified attestation
- npm trusted publishing (OIDC): yes
- Install scripts: suspicious script found
- Prompt-injection scan: not run
- Obfuscation scan: not run
- Evidence age: 0 days

## Security scan

- **Status:** warnings
- **Scanned:** 2026-10-10T07:01:47.131Z
- **Version scanned:** 0.1.15
- **CVEs:** none found by OSV at scan time
**Findings**
- injection-shaped content (warning) in the `scan_text` tool: Exfiltration-shaped instruction

## Tools

5 declared. Statically extracted from the shipped source — a floor on the surface, not a census.
- `scan_text` — Scan a raw text string (e.g. a prompt you're about to send to an LLM) for leaked credentials (API keys, private keys, JWTs) and PII (TC Kimlik No, credit card, 
- `scan_messages` — Scan an OpenAI/Anthropic-style chat request body (a JSON object with a `messages` array and/or a `system` field) for leaked credentials and PII in every message
- `scan_file` — Scan a single file — plain text, or a JSON chat-request-body fixture (auto-detected) — for leaked credentials and PII
- `scan_directory` — Recursively scan a directory of prompt logs or request-body fixtures for leaked credentials and PII
- `list_patterns` — List every credential/PII pattern this scanner detects, grouped by category

## Install

**Verdict: do-not-install** — Do not install: 1 injection-shaped pattern found in this entry's own text — it may try to steer the model that loads it.
**Blocking**
- 1 injection-shaped pattern found in this entry's own text — it may try to steer the model that loads it. — tool:scan_text: Exfiltration-shaped instruction
**Client configuration withheld.** Client configs are withheld because this entry has a blocking finding. Show the warnings below to the person installing it.
If they have seen the findings and still want to proceed, request the plan again with acknowledge_warnings=true.

## Blast radius

Contained to moderate — no credential declaration found, from the publisher, the upstream registry, or the README. Known so far: runs on your machine; read-only tool surface.
- Floor 13, ceiling 31 (tier: unknown)
- `unknown` means the floor and ceiling land in different bands — not measured enough to name one. It does not mean low.
- This is impact, not likelihood. A high radius is not a defect: a filesystem server is supposed to write files. It is never part of the trust score.

## Machine-readable views of this entry

- Signed JSON: https://forgeregistry.com/api/v1/packages/%40guardbee%2Fmcp-prompt-leak-scanner
- Install plan: https://forgeregistry.com/api/v1/packages/%40guardbee%2Fmcp-prompt-leak-scanner/install-plan
- Alternatives: https://forgeregistry.com/api/v1/alternatives/%40guardbee%2Fmcp-prompt-leak-scanner
- HTML page: https://forgeregistry.com/registry/%40guardbee%2Fmcp-prompt-leak-scanner
- MCP: POST https://forgeregistry.com/api/mcp → `forge_get_package` / `forge_install_plan`

## About this document

Generated by Forge (https://forgeregistry.com) — a compact rendering of the same record served, signed, at the JSON URL above. Trust and scan facts are the registry's own measurements; anything Forge did not measure is named as unmeasured rather than omitted.