Injectshield
Prompt-injection firewall for AI agents — scan untrusted text before LLM calls.
Description supplied by the publisher; it is a claim, not verified evidence.
- Name
- io.github.bch1212/injectshield
- Listed in
- Official MCP Registry
- Publisher
- bch1212
- Latest version
- 0.1.4
- Published
- 2026-05-06
- License
- MIT
- Evidence
- Analyzed by UND Assay