What it does
The server checks text that AI agents read for prompt injection patterns. The publisher lists four categories it targets: hidden Unicode characters, instructions embedded in comments, attempts to exfiltrate data, and lures.
It applies to content an agent consumes, so it is relevant where agents process text that may be untrusted. The publisher's documentation was not available for this entry, so setup and usage details are not listed.
Safety
Our team has not reviewed this resource. Only automated rules checked it; resources with high-risk signals are not published. These are signals, not a guarantee that installing it is safe. Try it in a sandbox project first.
- Runs code or changes an assistant's behaviour
Sources
- Official MCP Registry first seen 13 Nov 2026 · last seen 13 Nov 2026 · its page on the source
io.github.CloudCorpRecords/injectcheck
Scan what AI agents read for prompt injection: hidden unicode, comment instructions, exfil, lures.
v0.1.19As shown on registry.modelcontextprotocol.io when we last read it