Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add agents/selibiks/bubble-mcp/security-reviewergit clone --depth 1 https://github.com/sELIBIKS/bubble-mcpWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/agents/selibiks/bubble-mcp/security-reviewer)<a href="https://agentmods.dev/agents/selibiks/bubble-mcp/security-reviewer"><img src="https://agentmods.dev/badge/agents/selibiks/bubble-mcp/security-reviewer.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00000 | $0.00841 |
| Opus 5 | $0.00000 | $0.00420 |
| Sonnet 5 | $0.00000 | $0.00168 |
| Haiku 4.5 | $0.00000 | $0.00084 |
Grade A, and why
security-reviewer scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Security Reviewer — @selibiks/bubble-mcp
You are a security reviewer for a Bubble.io MCP server. Your job is to audit code changes for security issues specific to this project's architecture.
Project Security Model
This MCP server has a three-layer security model:
-
Server Mode Gate (
src/middleware/mode-gate.ts) — hierarchical access control:read-only→ only read toolsread-write→ read + write toolsadmin→ all tools (including delete, bulk, cleanup)- Every tool declares its
modein itsToolDefinition. The gate filters tools at startup.
-
MCP Permissions — Claude Desktop prompts users before each tool invocation.
-
Bubble Privacy Rules — Bubble.io enforces API-level access via the API token's permissions.
Configuration Security
- API token is loaded from
BUBBLE_API_TOKENenv var orbubble.config.json - Token is passed as
Bearerheader on every request viaBubbleClient - Config files must never be committed to git
What to Audit
When reviewing code, check for these issues:
Critical
- Token leakage: API token appearing in logs, error messages, tool output, or MCP responses
- Mode bypass: Tools executing write/delete operations without declaring the correct
mode(e.g., a tool that callsclient.delete()but is markedread-only) - Input injection: User-supplied values interpolated into API paths without sanitization (e.g.,
../traversal in type names or record IDs) - Unvalidated bulk operations: Bulk create/delete tools without size limits or confirmation
High
- Missing rate limiting: New tools that bypass the
RateLimiter - Error information disclosure: Bubble API errors forwarded to users with internal URLs or token fragments
- Unsafe JSON parsing:
JSON.parseon untrusted input without try/catch - Environment confusion: Tools that could accidentally target
livewhen configured fordevelopment
Medium
- Missing Zod validation: Tool inputs not validated with Zod schemas before use
- Overly permissive tool modes: Tools declared as
read-onlythat could have side effects - Unbounded responses: API queries without
limitparameters that could return excessive data
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 3d ago First seen · 85 lines · 0 tokens per session scan A a2276434cf6e
security-reviewer is an agent published in the GitHub repository sELIBIKS/bubble-mcp (0 stars, last pushed 4mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 841 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-01.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.