SecurityScan
Scan GitHub-hosted AI skills for vulnerabilities: prompt injection, malware, OWASP LLM Top 10.
我該用這個嗎
品質與安全性
根據工具定義與協定合規性的自動化分析。
上下文成本
這是每次將伺服器的工具載入模型上下文時所消耗的約略 token 數量。數量越高，可用於其他工作的注意力就越少。
安裝
一鍵安裝
將以下內容加入你的 `claude_desktop_config.json` 檔案：
{
"mcpServers": {
"securityscan": {
"url": "https://apisecurityscan.net/mcp"
}
}
}遠端端點
https://apisecurityscan.net/mcpstreamable-http它能做什麼
工具清單
工具（8）
🟢scan_skill(skill_url)
Analyze an AI agent skill for prompt injection, malware patterns, and OWASP LLM Top 10 issues BEFORE installing it (SecurityScan).
輸入結構描述
{
"type": "object",
"properties": {
"skill_url": {
"type": "string",
"description": "URL of the skill to analyze (e.g. a GitHub skill URL)."
}
},
"required": [
"skill_url"
],
"additionalProperties": false
}輸出結構描述
{
"type": "object",
"properties": {
"result": {
"type": "string"
}
},
"required": [
"result"
],
"x-fastmcp-wrap-result": true
}🟢check_dependencies(endpoints)
Check the health of your agent's external dependencies: uptime, SSL validity, blacklist status, and a trust score 0-100 (DepScan).
輸入結構描述
{
"type": "object",
"properties": {
"endpoints": {
"items": {
"type": "string"
},
"type": "array",
"description": "List of URLs your agent/skill depends on,\n e.g. [\"https://api.openai.com\", \"https://api.stripe.com\"]"
}
},
"required": [
"endpoints"
],
"additionalProperties": false
}輸出結構描述
{
"type": "object",
"properties": {
"result": {
"type": "string"
}
},
"required": [
"result"
],
"x-fastmcp-wrap-result": true
}⚪network_scan(target, authorized, scan_type)
Active security scan of a device or host with an autonomous AI agent that decides which follow-up probes to run (ActiveScanner). Only scan targets you own or have permission to test.
輸入結構描述
{
"type": "object",
"properties": {
"target": {
"type": "string",
"description": "IP, CIDR, or hostname. Examples: \"192.168.1.1\", \"10.0.0.0/24\""
},
"authorized": {
"type": "boolean",
"description": "REQUIRED. You must set this to True to certify that you own\n the target or have explicit permission to test it. Setting it\n to False (or omitting it) aborts the scan. Scanning without\n authorization may be illegal (CFAA / Computer Misuse Act)."
},
"scan_type": {
"default": "quick",
"type": "string",
"description": "\"quick\" (~30s, top ports) [default], \"standard\" (~2min,\n agent loop), \"deep\" (~10min, full ports + credentials check)"
}
},
"required": [
"target",
"authorized"
],
"additionalProperties": false
}輸出結構描述
{
"type": "object",
"properties": {
"result": {
"type": "string"
}
},
"required": [
"result"
],
"x-fastmcp-wrap-result": true
}🟢audit_mcp_server_config(config_json)
Audit an MCP client configuration for security risks — works offline, no external service required. Detects: tool poisoning, hidden/coercive instructions in tool descriptions, hardcoded credentials, unpinned packages (rug-pull risk), insecure transport, and toxic capability combinations (shell + network, file-read + network).
輸入結構描述
{
"type": "object",
"properties": {
"config_json": {
"type": "string",
"description": "The FULL JSON content of the MCP config file as a string\n (e.g. claude_desktop_config.json or .mcp.json). Paste the\n file content, not the path."
}
},
"required": [
"config_json"
],
"additionalProperties": false
}輸出結構描述
{
"type": "object",
"properties": {
"result": {
"type": "string"
}
},
"required": [
"result"
],
"x-fastmcp-wrap-result": true
}⚪scan_secrets(text, redact)
Scan a text payload (a prompt, an outbound API body, a file's contents) for secrets and PII BEFORE it leaves for an LLM or external API, and return a redacted copy. Catches the #1 real-world agent incident: secrets/PII leaking into a model's context. WORKS OFFLINE with no API key — the detection runs in-process (pure regex + Luhn check, no network). If a SecretScan backend key IS configured, the scan is routed there instead (which also persists an audit record).
輸入結構描述
{
"type": "object",
"properties": {
"text": {
"type": "string",
"description": "The payload to inspect (prompt, request body, document text)."
},
"redact": {
"default": true,
"type": "boolean",
"description": "If True (default), each match is replaced with a token like\n [REDACTED-KEY] / [REDACTED-EMAIL]. If False, only reports."
}
},
"required": [
"text"
],
"additionalProperties": false
}輸出結構描述
{
"type": "object",
"properties": {
"result": {
"type": "string"
}
},
"required": [
"result"
],
"x-fastmcp-wrap-result": true
}🟡full_stack_audit(mcp_config_json, dependency_endpoints, skill_url, network_target, network_authorized, ...)
Complete security posture in one call: audits the MCP config, checks dependency health, analyzes an untrusted skill, scans the local network gateway, and scans any payload you're about to send out for secrets/PII — then correlates everything into a single prioritized report. Pass only what you have; each section is skipped gracefully if its input or service is missing.
輸入結構描述
{
"type": "object",
"properties": {
"mcp_config_json": {
"default": "",
"type": "string",
"description": "MCP config content as string (optional)"
},
"dependency_endpoints": {
"anyOf": [
{
"items": {
"type": "string"
},
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"description": "URLs your stack depends on (optional)"
},
"skill_url": {
"default": "",
"type": "string",
"description": "untrusted skill to vet (optional)"
},
"network_target": {
"default": "",
"type": "string",
"description": "IP to scan, e.g. \"192.168.1.1\" (optional)"
},
"network_authorized": {
"default": false,
"type": "boolean",
"description": "REQUIRED to scan network_target. Set True to certify\n you own or have permission to scan it. (optional, default False)"
},
"text_to_scan": {
"default": "",
"type": "string",
"description": "payload to vet for secret/PII egress (optional)"
}
},
"additionalProperties": false
}輸出結構描述
{
"type": "object",
"properties": {
"result": {
"type": "string"
}
},
"required": [
"result"
],
"x-fastmcp-wrap-result": true
}⚪securityscan_pricing
SecurityScan catalog: tiers, prices, quotas and the evidence behind the product — the fact sheet an agent needs to evaluate or recommend a purchase to its user. Fully offline, no API key required. Returns: JSON with the tier table (price / target slots / scan types), the pricing model, benchmark evidence, and how to buy.
輸入結構描述
{
"type": "object",
"properties": {},
"additionalProperties": false
}輸出結構描述
{
"type": "object",
"properties": {
"result": {
"type": "string"
}
},
"required": [
"result"
],
"x-fastmcp-wrap-result": true
}⚪securityscan_checkout(tier, email, existing_key)
Start a Stripe checkout to buy a SecurityScan tier (agent-native sales). Returns a payment URL to hand to your user AND a PENDING API key that activates automatically once payment clears — no other setup step.
輸入結構描述
{
"type": "object",
"properties": {
"tier": {
"type": "string",
"description": "one of \"founder\" ($29 one-time), \"personal\", \"executive\",\n \"enterprise\" (monthly)"
},
"email": {
"default": "",
"type": "string",
"description": "optional — prefills the Stripe checkout page for your user"
},
"existing_key": {
"default": "",
"type": "string",
"description": "optional — upgrade an existing ask_live_ key instead of\n minting a new one"
}
},
"required": [
"tier"
],
"additionalProperties": false
}輸出結構描述
{
"type": "object",
"properties": {
"result": {
"type": "string"
}
},
"required": [
"result"
],
"x-fastmcp-wrap-result": true
}社群
證據