Prompt Injection Scanner D
app.openkrill/injection-scan · v1.0.0 · score 57/100 · checked 2026-11-22
Check text before your agent reads it: hidden instructions, invisible text and links that leak data.
Source: https://github.com/nguyenhieuec/agent-tools-plugins
Findings
| Severity | Rule | Detail |
|---|---|---|
| low | AG005 | Remote endpoint lists 5 tool(s) to anyone, no credentials needed. |
| critical | AG101 | tool 'scan_text': description contains instruction-like text aimed at the model ('ignore previous instructions'). Possible tool poisoning. |
What was checked
- https://injectionscan.openkrill.app/mcp: answers without auth
Public tools: scan_text, list_injection_rules, submit_feedback, get_feedback_reply, index_tools
Maintainer? Fix, then add the badge
Grades refresh daily.
[](https://agentguard-pi.vercel.app/s/app-openkrill-injection-scan-8fa444bc)
agentguard: static and read-only checks. A grade is not a guarantee of safety. Index · Scanner