mcp-server-security SKILL.md skillA
mcp-server-security from sigistry/marketplace is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add sigistry/marketplace/mcp-server-security@git:20260826.571bc2fPins git:20260826.571bc2f in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- sigistry/marketplace
- Path
plugins/mcp-server-smith/skills/mcp-server-security/SKILL.md- Versions recorded
- 2
- Latest version
- git:20260826.571bc2f, committed Aug 26, 2026
- First version recorded
- Aug 2, 2026
- Size
- 5,225 bytes
- Repository stars
- 3
- License
- MIT
This skill should be used when the user mentions "MCP security", "MCP server security", "prompt injection", "tool poisoning", "confused deputy", "token passthrough", "MCP threat model", "command injection", "SSRF", "rate limiting MCP", "MCP CORS", or hardening a Model Context Protocol server against attack. It provides the MCP threat model and per-risk mitigations.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# MCP Server Security ## Purpose An MCP server is an **attack surface an AI agent invokes on the user's behalf**, which combines two threat models: ordinary service security (injection, SSRF, secrets, DoS) and LLM-specific risks (prompt/tool-poisoning injection, confused deputy). Because the model will call tools with attacker-influenced arguments and read back tool/resource content into its context, a small server flaw becomes an agent-level compromise. This skill is the threat model and the mitigations to apply and to audit for. It complements `mcp-authorization` (identity/access) with the rest of the surface. ## The threat model, by trust boundary | Boundary | Risk | Mitigation | |---|---|---| | Client → server identity | confused deputy, token passthrough | validate `aud`; never forward the incoming token (see `mcp-authorization`) | | Tool arguments → system calls | command / SQL / path injection, SSRF | validate + parameterize; allowlist; never build shells/URLs from raw args | | Server → model (tool/resource output) | prompt injection, tool poisoning | treat all returned content as untrusted; do not let it carry instructions | …
Read the whole file at its exact version.
How to install
mdr add sigistry/marketplace/mcp-server-security@sha256:d4d43ccf758af0c0The line at the top of this page pins the label git:20260826.571bc2f, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_lv6gbzoufiwzg5wy)
3 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 2 versions of this file, between Aug 2, 2026 and Aug 26, 2026, about one every 23 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260826.571bc2f latest | 2026-08-26 | 571bc2f | 5,225 B | A | view · diff |
| git:20260802.9f9bd44 | 2026-08-02 | 9f9bd44 | 5,225 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (5225 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
sigistry/marketplace · 3 stars · license MIT · pushed 2026-11-06 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_lv6gbzoufiwzg5wy GET https://markdownregistry.com/api/v1/resolve?ref=sigistry/marketplace/mcp-server-security GET https://markdownregistry.com/api/v1/blob/d4d43ccf758af0c04f014f440e5e24d42792d6249ba5ae896d8b0b92f3682669
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.