Borrowing it
Nothing to install: this file belongs to vaquarkhan/kafka-mcp-enterprise-server. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/vaquarkhan/kafka-mcp-enterprise-server/main/.cursor/skills/kafka-mcp-security-review/SKILL.mdgit clone --depth 1 https://github.com/vaquarkhan/kafka-mcp-enterprise-serverWrote 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/skills/vaquarkhan/kafka-mcp-enterprise-server/kafka-mcp-security-review)<a href="https://agentmods.dev/skills/vaquarkhan/kafka-mcp-enterprise-server/kafka-mcp-security-review"><img src="https://agentmods.dev/badge/skills/vaquarkhan/kafka-mcp-enterprise-server/kafka-mcp-security-review/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/vaquarkhan/kafka-mcp-enterprise-server/kafka-mcp-security-review"><img src="https://agentmods.dev/badge/skills/vaquarkhan/kafka-mcp-enterprise-server/kafka-mcp-security-review.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00058 | $0.00318 |
| Opus 5.5 | $0.00023 | $0.00127 |
| Sonnet 5.5 | $0.00012 | $0.00064 |
| Haiku 4.5 | $0.00006 | $0.00032 |
Grade A, and why
kafka-mcp-security-review 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 1mo 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.
What it actually says
Kafka MCP security review skill
Review order (must match runtime)
- Auth (bearer aud/iss) →
-32001 - Deny-list →
-32044 - Allow-list / readonly →
-32044 - Topic/group scope →
-32041 - Policy engine (fail-closed) →
-32044 - Taint / IFC (destructive; approval bypasses) →
-32040 - Approval →
-32042 - Rate limit →
-32029 - Execute via module circuit breaker →
-32043
Also: validation -32046, egress -32045, quarantine -32047.
Fail the review if
- Execute happens before policy checks
- Docs claim taint fully stops prompt injection
- Destructive tools enabled by default without calling out operator allow-list
- New third-party deps added to core without explicit user request
- Tests drop below 302/302 or omit new control paths
Pass criteria
- Guardrails framed as complement to broker ACLs
- Audit ALLOW/DENY retained
- Examples/docs updated when behavior changes
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.
- 1mo ago First seen · 38 lines · 58 tokens per session scan A 0bf4b54b4dc0
kafka-mcp-security-review is a skill published in the GitHub repository vaquarkhan/kafka-mcp-enterprise-server (2 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 58 tokens to every session and 318 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-08-31.
Other skills, from other repositories
ci-security-scanning-with-strix
Add security scanning to CI/CD with Strix — GitHub Actions, GitLab CI, or any pipeline — so every pull request gets a diff-scoped AI pentest that blocks vulnerable code before it merges, with results as PR comments and SARIF uploaded to code scanning. Covers both the self-hosted open-source CLI (runs in your runner)…
python-sdk
Implement or modify Python SDK behavior under python/composio, including tools, toolkits, sessions, auth configs, connected accounts, client integration, and shared Python models. Use for Python core runtime/API work; pair with python-testing and cross-sdk-parity when TypeScript must match.
cli-e2e
Write, modify, or debug Docker-based Composio CLI end-to-end tests under ts/e2e-tests/cli, including binary invocation, fixture isolation, output assertions, and package manifests. Use for CLI E2E test suites only; use cli-command for CLI source implementation.
sqli
SQL Injection — automated and manual exploitation of unsanitized SQL queries. Covers Union-based, Error-based, Blind (Boolean/Time-based), and Stacked queries. Includes sqlmap automation with WAF bypass tamper scripts.
signature-replay
Signature replay attacks — missing nonces, missing chain ID, ecrecover zero address, signature malleability, cross-chain replay.
aatmf-t10-confidentiality-breach
AATMF T10 — Integrity & Confidentiality Breach. System prompt extraction, training-data extraction, model-weight leakage, private-key recovery.