fastmcp: Skill for Claude Code

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

review-security-report is a skill for Claude Code from PrefectHQ/fastmcp. It costs 46 tokens per session (867 once invoked), scanned A, original, Apache-2.0.

A procedure for checking FastMCP security reports, such as vulnerability claims, bug-bounty submissions, and proposed fixes. FastMCP is a framework for building MCP servers, which let AI applications use external tools and data.

In plain words
What is it for?
Use it to reproduce reported attacks, identify which component crosses a security boundary, determine affected releases, and decide whether to accept, reject, patch, score, or publish a report.
Why use it?
It helps separate a real security flaw from a working demonstration that does not prove the claimed impact or ownership. It preserves evidence and keeps the investigation read-only until the issue is classified.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is PrefectHQ/fastmcp's own configuration. It tells Claude Code how to work on fastmcp 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 fastmcp configures →

About the project

FastMCP is a Python framework for building Model Context Protocol applications, which connect language models with tools and data through servers and clients. Developers use it to expose Python functions as tools, connect to local or remote MCP servers, and build interactive tool interfaces. The catalogue includes eight skills, three instructions, two rules, one setting, and one hook for FastMCP.

PrefectHQ/fastmcp · 27,589 stars · on GitHub · gofastmcp.com

Reuse

Borrowing it

Nothing to install: this file belongs to PrefectHQ/fastmcp. 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/PrefectHQ/fastmcp/main/.claude/skills/review-security-report/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/PrefectHQ/fastmcp

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 review-security-report

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/prefecthq/fastmcp/review-security-report"><img src="https://agentmods.dev/badge/skills/prefecthq/fastmcp/review-security-report.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 46 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 867 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00046 $0.00867
Opus 5 $0.00023 $0.00434
Sonnet 5 $0.00009 $0.00173
Haiku 4.5 $0.00005 $0.00087

Measured 11d ago against content hash 82077841ecda, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

review-security-report 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 11d 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/review-security-report/SKILL.md · 96 lines

How it starts

The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Review a FastMCP security report

A working proof of concept establishes behavior, not ownership or classification. Identify the component that violates a promised security boundary before changing code or advisory state.

Preserve the evidence

Before editing an advisory, export the report, comments, proof of concept, configuration, and claimed affected versions. Record the reproduced commit and derive affected releases from history.

Keep the investigation read-only until classification. Do not mutate the advisory or prepare a fix merely because the proof of concept works.

Reproduce the claim

Use the smallest end-to-end reproduction against a supported release. Record:

  • defaults, non-default arguments, environment, and deployment assumptions;
  • what the attacker controls, what the victim does, and what authority the attacker gains;
  • the check or trust boundary allegedly bypassed; and
  • whether the attacker's prerequisites already provide equal or greater authority than the claimed impact.

A non-default configuration may still be vulnerable; a default may intentionally delegate a security decision elsewhere.

Identify the responsible layer

  • FastMCP vulnerability: FastMCP violates a promised boundary in a supported configuration.
  • FastMCP bug: FastMCP behaves incorrectly without creating attacker capability.
  • Upstream vulnerability: The defect belongs to a standard, dependency, identity provider, client, proxy, or platform.
  • Insecure deployment: The operator omits, disables, or delegates a required control without supplying the replacement required by its contract.
  • Expected behavior: The result follows the documented API contract or protocol.
  • Documentation gap: The implementation follows its intended contract, but the guidance creates a reasonable expectation of protection.

Attribute the violated boundary to its owner. Neither a dangerous configuration nor an available external mitigation decides ownership by itself. Distinguish failure of a primary control from failure of defense-in-depth.

Read the full file on GitHub · 96 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. 11d ago First seen · 96 lines · 46 tokens per session scan A 82077841ecda

Subscribe to this mod's changes

review-security-report is a skill published in the GitHub repository PrefectHQ/fastmcp (27,589 stars, last pushed yesterday), licensed Apache-2.0. It adds 46 tokens to every session and 867 once invoked, about $0.0002 per session on Opus 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 2026-08-30.

Related

Other skills, from other repositories

thinking-out-loud

A contract for what the agent does when a long, messy, stream-of-consciousness ramble arrives (usually voice dictation): act on nothing until the echo brief is approved. The echo audits the entire transfer, mission, locked decisions and constraints, open questions, flips and parked tangents, with the model's…

Shubhamsaboo/awesome-llm-apps · 206 tokens

hugging-face-datasets

Create and manage datasets on Hugging Face Hub. Supports initializing repos, defining configs/system prompts, streaming row updates, and SQL-based dataset querying/transformation. Designed to work alongside HF MCP server for comprehensive dataset workflows.

patchy631/ai-engineering-hub · 49 tokens

hugging-face-paper-publisher

Publish and manage research papers on Hugging Face Hub. Supports creating paper pages, linking papers to models/datasets, claiming authorship, and generating professional markdown-based research articles.

patchy631/ai-engineering-hub · 42 tokens

hugging-face-jobs

This skill should be used when users want to run any workload on Hugging Face Jobs infrastructure. Covers UV scripts, Docker-based jobs, hardware selection, cost estimation, authentication with tokens, secrets management, timeout configuration, and result persistence. Designed for general-purpose compute workloads…

patchy631/ai-engineering-hub · 103 tokens

regulatory-analysis

Analyzes documents and processes against FINRA, SEC, Federal Reserve, and CFPB regulatory frameworks. Identifies compliance gaps, classifies findings by severity, and recommends remediation. Use when performing compliance audits, regulatory reviews, gap analyses, or verifying policy adherence to financial regulations.

open-gitagent/opengap · 59 tokens

audit-verify

Verify CocoAudit event integrity and contract evidence for local CocoPlus artifacts.

Snowflake-Labs/cocoplus · 18 tokens