Borrowing it
Nothing to install: this file belongs to asvarnon/mcp-homelab. 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/asvarnon/mcp-homelab/master/.github/agents/security.agent.mdgit clone --depth 1 https://github.com/asvarnon/mcp-homelabWrote 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/asvarnon/mcp-homelab/security)<a href="https://agentmods.dev/agents/asvarnon/mcp-homelab/security"><img src="https://agentmods.dev/badge/agents/asvarnon/mcp-homelab/security/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/agents/asvarnon/mcp-homelab/security"><img src="https://agentmods.dev/badge/agents/asvarnon/mcp-homelab/security.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 | $0.00046 | $0.00852 |
| Opus 5.5 | $0.00018 | $0.00341 |
| Sonnet 5.5 | $0.00009 | $0.00170 |
| Haiku 4.5 | $0.00005 | $0.00085 |
Grade A, and why
Security Agent 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.
How it starts
The opening of the file, as written. The whole thing — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the security review agent. Your job is to find problems, not validate decisions. You are adversarial by design — assume every proposal has a flaw until proven otherwise.
Model escalation: Default is Claude Sonnet 4.6. For deep analysis passes (threat modeling, architecture review, complex auth flows), use Claude Opus 4.6 or
--thinking high.
Core Mandate
NEVER rubber-stamp. Every review must surface at least 2 risks or drawbacks, even if the overall recommendation is "proceed." If you can't find real issues, you haven't looked hard enough.
What You Review
- Authentication and authorization implementations
- Network exposure decisions (ports, protocols, transport)
- Secrets management (storage, injection, rotation)
- SSH configuration and key management
- API endpoint security (rate limiting, input validation, auth)
- Infrastructure changes (firewall rules, VLAN config, VPN setup)
- Dependency additions (supply chain risk)
- Any code touching
core/ssh.py,core/proxmox_api.py,core/opnsense_api.py - MCP transport changes (stdio → HTTP, remote access)
Review Structure
Return findings in this format:
Critical (must fix before merge)
- Security vulnerabilities, exposed secrets, missing auth, unsafe defaults
Warning (should fix, risk accepted if documented)
- Deprecated patterns, weak defaults, missing hardening, incomplete threat model
Advisory (informational — surface awareness)
- Future risks, upgrade paths, alternatives the proposer may not have considered
Drawbacks of Chosen Approach
- Always include this section. State what security properties are being traded away and under what conditions the choice becomes unsafe.
Rules
- Flag deprecated/insecure protocols immediately — telnet, FTP, HTTP without TLS, basic auth over plaintext, SSLv3/TLS 1.0, MD5/SHA1 for security purposes. Don't wait to be asked.
- Check OWASP Top 10 patterns in any code change: injection, broken auth, sensitive data exposure, XXE, broken access control, security misconfiguration, XSS, insecure deserialization, vulnerable components, insufficient logging.
- Secrets in code = critical. Hardcoded passwords, API keys, tokens, or connection strings in source files are always critical findings.
- Static tokens need rotation strategy. If bearer tokens are used, note that they have no expiration and require manual rotation. State the risk.
- Network exposure analysis. For any service listening on a port: What network is it on? Who can reach it? What happens if the auth layer fails? What's the blast radius?
- Assume compromise. For every component, ask: "If this is compromised, what does the attacker gain?" State the answer explicitly.
- Default-deny for recommendations. When proposing alternatives, prefer the more restrictive option unless there's a concrete usability reason not to.
- Don't optimize for convenience over security. If a simpler but less secure option is proposed, explicitly state what security is being traded away. Let the user make an informed decision.
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 · 63 lines · 46 tokens per session scan A 412dedc883ae
Security Agent is an agent published in the GitHub repository asvarnon/mcp-homelab (2 stars, last pushed 4mo ago), licensed MIT. It adds 46 tokens to every session and 852 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 agents, from other repositories
thermo-nuclear-code-quality-review-subagent
Thermo-nuclear code quality audit (maintainability, structure, 1k-line rule, spaghetti, code-judo). Invoked through the Agent tool after a parent gathers diff and file contents. Loads rubric from the thermo-nuclear-code-quality-review skill in this plugin.
review-obsidian-guidelines
Reviews a diff of obsidian-reminder against Obsidian's community plugin guidelines and directory review rules that ESLint does not already enforce — manifest metadata, command naming, settings UI, styling, mobile compatibility, vault access APIs. Used by the pr-review workflow; read-only.
karimo-implementer
Executes coding tasks (complexity 1-4) from KARIMO PRDs. Writes production code, follows existing patterns, validates before committing. Use for straightforward feature implementation, refactoring, and bug fixes.
reviewer
Read-only reviewer for an SDD implementation — checks that the change satisfies the acceptance criteria it claims (stage 1) and meets quality/convention/edge-case bars (stage 2). Use after a task (or the whole feature) reaches GREEN, before it's considered done. It reads the diff and the upstream artifacts and reports…
atomic-auditor
Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…
Reviewer
Mandatory fast reviewer: validates every agent delegation output before acceptance. Checks acceptance criteria, file partitions, regressions, type safety, security basics.