agentmods.dev

genefoundry-router: Skill for Claude Code

.claude/skills/security-review/SKILL.md

security-review is a skill for Claude Code from berntpopp/genefoundry-router. It costs 38 tokens per session (641 once invoked), scanned A, original, MIT.

A security checklist for the Genefoundry Router, the component that controls access between callers and backend services.

In plain words
What is it for?
Use it when reviewing the router, especially changes to authentication, proxies, logging, limits, or public deployment settings.
Why use it?
It helps catch unsafe authentication, token forwarding, network exposure, request limits, and error-handling configurations before deployment.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions AGENTS.md.

This is berntpopp/genefoundry-router's own configuration. It tells Claude Code how to work on genefoundry-router itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything genefoundry-router configures →

not rated 6repo 2d ago A scan 38 tokens original MIT
View source ↗ berntpopp/genefoundry-router genefoundry.org
Reuse

Borrowing it

Nothing to install: this file belongs to berntpopp/genefoundry-router. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/berntpopp/genefoundry-router/main/.claude/skills/security-review/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/berntpopp/genefoundry-router

Made for: Claude Code.

Wrote 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.

agentmods badge for security-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/berntpopp/genefoundry-router/security-review/github.svg)](https://agentmods.dev/skills/berntpopp/genefoundry-router/security-review)
Your own site
<a href="https://agentmods.dev/skills/berntpopp/genefoundry-router/security-review"><img src="https://agentmods.dev/badge/skills/berntpopp/genefoundry-router/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.

agentmods 80×15 button for security-review

Your own site · 80×15
<a href="https://agentmods.dev/skills/berntpopp/genefoundry-router/security-review"><img src="https://agentmods.dev/badge/skills/berntpopp/genefoundry-router/security-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 38 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 641 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00038 $0.00641
Opus 5.5 $0.00015 $0.00256
Sonnet 5.5 $0.00008 $0.00128
Haiku 4.5 $0.00004 $0.00064

Measured 1mo ago against content hash e553294287f7, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

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.

.claude/skills/security-review/SKILL.md · 26 lines

How it starts

The opening of the file, as written. The whole thing — 26 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Security Review (router)

Follow AGENTS.md first. The router is the trust boundary: it owns edge auth and must never forward the caller's token to backends. Ground in docs/SECURITY-ASSESSMENT-2026-06-29.md, docs/RESPONSE-ENVELOPE-STANDARD-v1.1.md (§Error-message sanitation), and the FastMCP not-found reflection guard.

Checklist

  1. No token passthrough — every proxy client goes through make_proxy_client() (in composition.py) with forward_incoming_headers=False; the caller's Authorization is never re-sent to a backend (fastmcp's ProxyClient default forwards it — regression-tested in tests/unit/test_no_token_passthrough.py).
  2. Secure-by-default — the startup guard (is_insecure_public_bind in cli.py, flag GF_ALLOW_INSECURE in config.py) refuses GF_AUTH_MODE=none on a non-loopback bind unless GF_ALLOW_INSECURE=true.
  3. Auth wiring — audience-bound JWTVerifier, RFC 9728 Protected Resource Metadata, WWW-Authenticate, OAuth proxy; audience = the …/mcp resource (RFC 8707), tolerant of a duplicated /mcp.
  4. Origin validation on (DNS-rebinding MUST); Streamable HTTP only, no SSE.
  5. Inbound limits — body-size cap (GF_MAX_BODY_BYTES) and opt-in rate limit (GF_RATE_LIMIT_RPM); outbound GF_BACKEND_TIMEOUT.
  6. PII-safe audit log — tool / namespace / outcome / elapsed / correlation-id only; never args, results, or exception text.
  7. Backends not publicly reachable — expose-only behind the proxy; verify their ports aren't on the public IP.
  8. Tool-definition drift — make fleet-probe / genefoundry-router drift as a rug-pull / tool-poisoning tripwire; re-pin the baseline only after reviewing the diff.
  9. Error-message / identity sanitation — never reflect a caller-supplied tool / resource / prompt name or URI (grammar-valid but possibly nonexistent) into caller-visible error text, the structlog audit sink, or Prometheus labels; registry-unresolved names bucket to _unknown (safe_log_identity in observability.py), and the AggregateProvider provider-fault log is scrubbed (notfound_guard.py). See Response-Envelope v1.1 §Error-message sanitation and the FastMCP not-found reflection guard.

Read the full file on GitHub · 26 lines

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.

  1. 1mo ago First seen · 26 lines · 38 tokens per session scan A e553294287f7

Subscribe to this mod's changes

security-review is a skill published in the GitHub repository berntpopp/genefoundry-router (6 stars, last pushed 2d ago), licensed MIT. It adds 38 tokens to every session and 641 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.

Securityapi-gatewaybioinformaticsclaudeclinical-geneticsfastmcpgateway
Related

Other skills, from other repositories

experimental-design

Designs experiments and studies BEFORE data is collected — choosing a design, randomizing, blocking, and laying out treatment combinations so results are interpretable. Use whenever someone is planning a study, asks how to assign subjects/samples to groups, mentions randomization, blocking, stratification, controls…

K-Dense-AI/scientific-agent-skills · 201 tokens

exploratory-data-analysis

Performs bounded, local exploratory analysis of explicitly supported scientific files. Supports redacted CSV/TSV/JSON profiles; optional NumPy, HDF5, FASTA/FASTQ, and basic image metadata inspection; missingness/leakage audits; outlier and transformation sensitivity; and rigorous EDA report scaffolds. Other domain…

K-Dense-AI/scientific-agent-skills · 83 tokens

matlab

Builds, reviews, migrates, and plans MATLAB or GNU Octave numerical workflows. Use for arrays, tabular/time data, tests, projects, graphics, MAT files, and explicit Python interoperability.

K-Dense-AI/scientific-agent-skills · 44 tokens

scientific-visualization

Creates and audits truthful, accessible, publication-ready scientific figures with Matplotlib, Seaborn, or Plotly. Use it for figure design, multi-panel layouts, uncertainty and missing-data displays, color/contrast review, image metadata validation, and journal export planning.

K-Dense-AI/scientific-agent-skills · 59 tokens

pennylane

Builds and differentiates PennyLane quantum circuits, hybrid PyTorch or JAX models, molecular VQE and QAOA workflows. Use for variational quantum algorithms, quantum machine learning, simulator validation, and moving validated circuits to provider plugins. For hardware-specific compilation use qiskit or cirq; for…

K-Dense-AI/scientific-agent-skills · 74 tokens

latex-posters

Create professional research posters in LaTeX using beamerposter, tikzposter, or baposter. Support for conference presentations, academic posters, and scientific communication. Includes layout design, color schemes, multi-column formats, figure integration, and poster-specific best practices for visual communication.

beita6969/ScienceClaw · 60 tokens