Index of every page on this site: llms.txt
All skills
prefecthq avatar

/review-security-report

@12a2db1
by Prefectprefecthq/fastmcp29k stars
2,631
Run it yourself

Review FastMCP vulnerability reports before accepting, rejecting, patching, scoring, or publishing them. Use for security advisories, bug-bounty submissions, OAuth or MCP vulnerability claims, and proposed security fixes.

Use this Skill: https://skilld.dev/gh/prefecthq/fastmcp/review-security-report

Nothing lands on disk. Nothing to clean up.

Fork this Skill

Edit a local copy. It keeps the author and licence.

SKILL.md

≈61 tokens for metadata: the name and description. ≈1.1k when used: this file.

Description uses 3.1% of example budget

Before choosing a Skill, your Agent reads its name and description. All available Skills share that space.

  • A shorter description leaves more room for other Skills. This entry exceeds our 1% size suggestion.

In our Claude Code example, all Skill names and descriptions share 8,000 characters. This Skill uses ≈246 characters, or 3.1%.

The 1% threshold is a size suggestion. Longer descriptions can still fit.

Your model, settings, and other Skills decide how much text your Agent can read.

Example settings and source

The example uses a 200k-token context and default Claude Code settings. The count includes the name, description, separators, and when_to_use when present. Codex also counts local file paths.

Skit's source and limits: Codex 0.160.1, Claude Code 2.1.292.

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.

Establish FastMCP's contract

Read the code, released documentation, tests, and history. Determine:

  1. What FastMCP promises for the exact configuration, supported API, and affected releases.
  2. Whether the proof of concept bypasses, disables, or delegates that protection.
  3. Whether the behavior follows the implemented protocol despite any stricter FastMCP promise.

If the intended contract remains unclear, ask the subsystem maintainer before accepting the report or proposing a fix. Current code alone does not define supported product behavior.

Separate OAuth proxy boundaries

For OAuth proxy reports, check each layer independently:

  • Open DCR lets unknown clients register redirects; a matching attacker callback is not a redirect validation bypass.
  • FastMCP consent binds the downstream client; ordinary upstream consent binds FastMCP's shared app.
  • require_authorization_consent=False removes consent; "external" delegates equivalent consent and transaction binding outside FastMCP.
  • PKCE protects the verifier, not a code issued for a malicious client's own challenge.
  • Redirect allowlists are optional policy and can break hosted clients or open DCR.

Review the proposed fix independently

A patch can block the proof of concept and still be wrong. Verify that it:

  • fixes the violated boundary at its source and enforces the claimed property;
  • does not silently change an intentional default or opt-in contract; and
  • preserves supported workflows without assuming one replacement control is the only valid design.

Treat a change to the supported product contract as an enhancement requiring maintainer agreement, independently of the security report.

Classification checkpoint

Before any GitHub mutation, state the decisive configuration and affected versions, boundary owner, realistic impact, and one disposition:

  • accept a draft advisory and prepare a private patch;
  • request specific missing evidence;
  • route as a normal FastMCP bug or upstream issue;
  • close as expected behavior or an insecure deployment;
  • ask the relevant maintainer to decide the contract.

Separately recommend any documentation or warning clarification warranted by the investigation.

When rejecting a report, acknowledge any valid reproduction and explain the decisive precondition.

Source: SKILL.md on GitHub

No rule matched.

skilld matched fixed text patterns in SKILL.md and file names. Patterns miss obfuscated code.

skilld run checks every file with the same patterns. It asks for approval before it loads a Skill with a behavior marked Needs approval.

1 warning2mo3 checks · Risk SAFE
  • Gen Agent Trust Hub2mo

    This skill provides a set of procedural guidelines for security maintainers to triage and review vulnerability reports. It contains no executable code, dependencies, or malicious instructions.

  • Socket2mo

    No alerts

  • Snyk2mo

    Risk: MEDIUM · 1 issue

Signed by skilld at 12a2db1. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub yesterday.

Activeupdated 2 months ago

README badge

README badge for prefecthq/fastmcp/review-security-report