sipi.bot — Spend Firewall for AI Agents. Pre-spend transaction governance for autonomous agents. MCP server, HTTP API, CLI. 53/53 eval, MIT.
- capability exposure inferred + 24
- trust mitigators mixed − 3
inferred mixed
The A–E grade is our heuristic synthesis — a "review this" prompt, not a verdict. Each factor is tagged by what backs it: attested (a verifiable record), reported (a third party's claim), or inferred (our own heuristic, e.g. permissions). See methodology.
graded 4m ago · see ecosystem CVEs →
No known CVEs for this server.
- low dangerous code
env-secret-flows-to-network-js: A process environment value (often a secret/token) flows into a network call — possible credential exfiltration. (kindrat86-sipi-bot-2e0e974/integra
analyzed commit 2e0e974 · analyzer v28 · 1w ago
skills & prompt files 2
- agent-rules kindrat86-sipi-bot-2e0e974/CLAUDE.md
- agent-rules kindrat86-sipi-bot-2e0e974/public/agents.md
danger signals1
- suspicious endpoint eu.i.posthog.com (telemetry) kindrat86-sipi-bot-2e0e974/public/analytics.js :6
var POSTHOG_HOST = "https://eu.i.posthog.com";
[](https://mcpobservatory.com/servers/github:kindrat86/sipi-bot/security) Heuristic, inferred signals — false positives (legitimately powerful tools, forks, language ports) are expected. Treat each as "review this", not a verdict. See the ecosystem-wide picture on the security hub, or the fleet security of kindrat86.