# SecurityScan

> Scan GitHub-hosted AI skills for vulnerabilities: prompt injection, malware, OWASP LLM Top 10.

- name: net.apisecurityscan/securityscan
- version: 1.0.0
- connection class: R1 (autonomous)
- trust: 85/100
- quality: 79/100 (good)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/net.apisecurityscan%2Fsecurityscan
- tools: https://api.protogrid.dev/v1/servers/net.apisecurityscan%2Fsecurityscan/tools

**An agent can connect on its own if it already holds `X_API_KEY`, `X_API_KEY`.** Remote endpoint behind a static API key or header. The registry never sees the value; the agent fills the placeholder.

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "securityscan": {
      "type": "http",
      "url": "https://apisecurityscan.net/mcp",
      "headers": {
        "X-API-Key": "${X_API_KEY}",
        "Authorization": "${X_API_KEY}"
      }
    }
  }
}
```

Placeholders to fill: `${X_API_KEY}`, `${X_API_KEY}`.

## Trust

- hygiene: 100
- liveness: 100
- freshness: 45
- provenance: 85
- drivers: +repository +dns-namespace +website +reachable +uptime-100% -stale-232d
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 79/100 (good)

### protocol: 75 (weight 25)

- warn `protocol.modern`: newest supported version is 2025-11-25; 2026-07-28 not supported, older versions are deprecated until 2027-07-28
- n/a `protocol.stateless`: only applies to 2026-07-28 servers
- pass `protocol.transport`: streamable HTTP
- n/a `protocol.list_ttl`: only applies to 2026-07-28 servers

### authorization: n/a (weight 15)

- n/a `auth.prm`, `auth.as_metadata`, `auth.cimd`: no remote uses OAuth
- n/a `auth.secret_in_url`: no templated URL

### tool hygiene: 71 (weight 30)

- pass `tools.descriptions`: every tool has a description
- pass `tools.description_length`: descriptions are concise
- pass `tools.schemas`: every tool has an object input schema
- fail `tools.annotations`: no tool declares readOnlyHint or destructiveHint, so clients cannot tell safe calls from risky ones
- fail `tools.directory_hints`: no tool declares all four of readOnlyHint, destructiveHint, idempotentHint and openWorldHint; missing: scan_secrets (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); scan_skill (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); network_scan (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); …
- pass `tools.token_cost`: about 1,384 tokens to load every tool
- pass `tools.api_dump`: tools are not a one-to-one API dump

### stability: 100 (weight 15)

- pass `stability.changes`: no tool changes in 30 days
- pass `stability.rug_pull`: no tool changed its meaning under the same name

### dependencies: n/a (weight 15)

- n/a `deps.known_vulns`, `deps.mcp_sdk_version`, `deps.resolvable`: no npm or PyPI package

- tools: 8, about 1,384 tokens to load them all
- tool set hash: 57268cacf404037df1d5a7a469aff848
- badge: [![protogrid quality](https://protogrid.dev/badge/net.apisecurityscan/securityscan.svg)](https://protogrid.dev/servers/net.apisecurityscan/securityscan)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.

### Tool changes

_No tool definition changes recorded._

## Remotes

- https://apisecurityscan.net/mcp (streamable-http, auth api_key ${X_API_KEY}, reachable true, uptime30d 1)

## Packages

_none_

## Tools (8)

- `audit_mcp_server_config`: 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).
- `check_dependencies`: Check the health of your agent's external dependencies: uptime, SSL
validity, blacklist status, and a trust score 0-100 (DepScan).
- `full_stack_audit`: 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.
- `network_scan`: 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.
- `scan_secrets`: 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).
- `scan_skill`: Analyze an AI agent skill for prompt injection, malware patterns, and
OWASP LLM Top 10 issues BEFORE installing it (SecurityScan).
- `securityscan_checkout`: 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.
- `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.