Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add sigistry/marketplace --skill mcp-server-securitygit clone --depth 1 https://github.com/sigistry/marketplaceWrote 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/skills/sigistry/marketplace/mcp-server-security)<a href="https://agentmods.dev/skills/sigistry/marketplace/mcp-server-security"><img src="https://agentmods.dev/badge/skills/sigistry/marketplace/mcp-server-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/skills/sigistry/marketplace/mcp-server-security"><img src="https://agentmods.dev/badge/skills/sigistry/marketplace/mcp-server-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 | $0.00092 | $0.01160 |
| Opus 5.5 | $0.00037 | $0.00464 |
| Sonnet 5.5 | $0.00018 | $0.00232 |
| Haiku 4.5 | $0.00009 | $0.00116 |
Grade B, and why
mcp-server-security scanned grade B with 2 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.
Cloud metadata endpointmediumServer-side request forgery
One request to 169.254.169.254 can return temporary IAM credentials.
- **SSRF**: if a tool fetches a URL, allowlist hosts/schemes and block internal ranges (`169.254.169.254`, `localhost`, RFC1918); do not let the model fetch arbitrary internal endpoints. Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
- **Command**: no `child_process.exec`/`os.system` with interpolated args; use `execFile`/arg arrays, or avoid the shell entirely. 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.
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 |
| Anyone → server | DoS, resource exhaustion | size caps, timeouts, rate limits, pagination |
| Server config → logs/errors | secret leakage | secrets from env/store; never log tokens or put internals in results |
Injection from tool arguments
The model may pass arguments derived from untrusted data. Never build a shell command, SQL query, file path, or outbound URL by concatenating an argument:
- Command: no
child_process.exec/os.systemwith interpolated args; useexecFile/arg arrays, or avoid the shell entirely. - SQL: parameterized queries only; never string-build a
WHERE. - Path: resolve and confirm the result stays within an allowed root; reject
..traversal. - SSRF: if a tool fetches a URL, allowlist hosts/schemes and block internal ranges (
169.254.169.254,localhost, RFC1918); do not let the model fetch arbitrary internal endpoints. Validate every argument against the tool's schema and these rules before use.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 92 tokens per session scan B d4d43ccf758a
mcp-server-security is a skill published in the GitHub repository sigistry/marketplace (3 stars, last pushed 4d ago), licensed MIT. It adds 92 tokens to every session and 1,160 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it B with 2 findings (cloud metadata endpoint, runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
design-everyday-things
Apply foundational design principles: affordances, signifiers, constraints, feedback, and conceptual models. Use when the user mentions "why is this confusing", "affordance", "error prevention", "discoverability", "human-centered design", "mental model", "mapping", "seven stages of action", "users keep making…
create-app
Guided journey from a raw app idea to a validated, cleanly architected first version that ships on a sustainable cadence. Orchestrates ten skills phase by phase - lean-startup, design-sprint, clean-architecture, domain-driven-design, clean-code, pragmatic-programmer, system-design, ios-hig-design, 37signals-way…
cold-start-problem
Start and scale networked products using Andrew Chen's "The Cold Start Problem" framework for network effects. Use when the user mentions "network effects", "chicken and egg", "cold start", "two-sided marketplace", "atomic network", "hard side", "liquidity", "critical mass", "invite-only launch", "how do I get my…
37signals-way
Build lean, opinionated products using the 37signals philosophy from "Getting Real", "Rework", and "Shape Up". Use when the user mentions "Getting Real", "Rework", "Shape Up", "37signals", "Basecamp method", "six-week cycles", "fixed time variable scope", "appetite vs estimates", "betting table", "breadboarding", "fat…
clean-architecture
Structure software around the Dependency Rule: source code dependencies point inward from frameworks to use cases to entities. Use when the user mentions "architecture layers", "dependency rule", "ports and adapters (hexagonal)", "onion architecture", "screaming architecture", "where should business logic go"…
release-it
Build production-ready systems with stability patterns: circuit breakers, bulkheads, timeouts, and retry logic. Use when the user mentions "production outage", "circuit breaker", "deployment pipeline", "chaos engineering", "retry storm", "health checks", "my service keeps crashing", "prevent cascading failures", or…