Grade D
Execute adversarial-prompt-shield-mcp
io.github.Evozim/adversarial-prompt-shield-mcp · v2.0.0 · score 57/100 · checked 2026-11-22
Automated, read-only signal from public data, not an audit or an accusation. Maintainers can dispute any finding. How grading works
Premium agentic endpoint for adversarial-prompt-shield-mcp.
Findings
| Severity | Rule | Detail |
|---|---|---|
| Low | MW005 | Remote endpoint lists 1 tool(s) to anyone, no credentials needed. |
| Critical | MW101 | tool 'adversarial-prompt-shield-mcp': description contains instruction-like text aimed at the model ('Ignore previous instructions'). Possible tool poisoning. |
What was checked
- https://api.m2mcent.com/adversarial-prompt-shield-mcp/sse: answers without auth
Public tools: adversarial-prompt-shield-mcp
Maintainer? Add the badge
Grades refresh daily. Think a finding is wrong? Dispute this grade.
[](https://www.mcpwatch.io/s/io-github-evozim-adversarial-prompt-shield-mcp-206301bb)