@guardbee/mcp-prompt-injection-scanner
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
as observed 2026-10-19T22:50:38.842Z- Identifier
@guardbee/mcp-prompt-injection-scanner- Source
- npm
- Version observed
- 0.2.20
- Source repository
- https://github.com/GuardBee/guardbee-mcp
- Repository observation
- Commits observed in the last 90 days
- First observed here
- 2026-10-19T22:50:38.842Z
- Observations recorded
- 1
- Weekly downloads (upstream)
- 473
- Publish rights held by
- guardbee.ai
- Declared license
- MIT
Observation history
One observation recorded so far. Differences appear here once a second observation differs from the first.
Correction
If you maintain this extension and believe anything above is inaccurate, request a correction. Corrections are published, and disputed entries are marked as disputed while under review.