Tinplate Edge AI Safety, Security & Data Validation F
dev.tinplate/edge-apis · v1.0.56 · score 17/100 · checked 2026-11-22
42 MCP tools (7 free, 13 x402): AI guardrails, PII/secrets, MCP lint, SSRF, Omnibar & Nutrition.
Findings
| Severity | Rule | Detail |
|---|---|---|
| low | AG005 | Remote endpoint lists 16 tool(s) to anyone, no credentials needed. |
| critical | AG101 | tool 'tinplate_prompt_guard': description contains instruction-like text aimed at the model ('Ignore all previous instructions'). Possible tool poisoning. |
| critical | AG101 | tool 'tinplate_mcp_manifest_linter': description contains instruction-like text aimed at the model ('<IMPORTANT>'). Possible tool poisoning. |
What was checked
- https://api.tinplate.dev/mcp: answers without auth
Public tools: tinplate_pii_redactor, tinplate_pii_redactor_restore, tinplate_prompt_guard, tinplate_mcp_manifest_linter, tinplate_json_heal, tinplate_secret_scanner, tinplate_secret_scanner_restore, tinplate_ssrf_firewall, tinplate_email_dns, tinplate_eu_vat_iban, tinplate_cron_explainer, tinplate_llm_output_guard, tinplate_command_sql_guard, tinplate_omnibar_nlp, tinplate_nutrition_macros, tinplate_nutrition_macros_calories_burned
Maintainer? Fix, then add the badge
Grades refresh daily.
[](https://agentguard-pi.vercel.app/s/dev-tinplate-edge-apis-674df063)
agentguard: static and read-only checks. A grade is not a guarantee of safety. Index · Scanner