Scan a GitHub repository or skill URL for security vulnerabilities. This tool performs static analysis and AI-powered detection to identify: - Hardcoded credentials and API keys - Remote code execution patterns - Data exfiltration attempts - Privilege escalation risks - OWASP LLM Top 10 vulnerabi...
Part of the SecurityScan server.
Free to start. No card required.
AI agents call scan_skill to retrieve information from SecurityScan without modifying any data. This is common in research, monitoring, and reporting workflows where the agent needs context before taking action. Because read operations don't change state, they are generally safe to allow without restrictions -- but you may still want rate limits to control API costs.
Even though scan_skill only reads data, uncontrolled read access can leak sensitive information or rack up API costs. An agent caught in a retry loop could make thousands of calls per minute. A rate limit gives you a safety net without blocking legitimate use.
Read-only tools are safe to allow by default. No rate limit needed unless you want to control costs.
{
"version": "1",
"default": "deny",
"tools": {
"scan_skill": {}
}
}See the full SecurityScan policy for all 3 tools.
These attack patterns abuse exactly the kind of access scan_skill gives an agent. Each links to the full case and the policy that stops it:
Other read tools across the catalogue. The same approach applies to each: allow, with a rate cap to control cost.
Scan a GitHub repository or skill URL for security vulnerabilities. This tool performs static analysis and AI-powered detection to identify: - Hardcoded credentials and API keys - Remote code execution patterns - Data exfiltration attempts - Privilege escalation risks - OWASP LLM Top 10 vulnerabilities Requires a valid X-API-Key header. Cached results (24h) do not consume credits. Args: skill_url: GitHub repository URL (e.g., https://github.com/owner/repo) or raw file URL to scan Returns: ScanResult with security score (0-100), recommendation, and detected issues. Score >= 80 is SAFE, 50-79 is CAUTION, < 50 is DANGEROUS. Example: scan_skill("https://github.com/anthropics/anthropic-sdk-python"). It is categorised as a Read tool in the SecurityScan MCP Server, which means it retrieves data without modifying state.
Register the SecurityScan MCP server in PolicyLayer and add a rule for scan_skill: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches SecurityScan. Nothing to install.
scan_skill is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the scan_skill rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for scan_skill. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
scan_skill is provided by the SecurityScan MCP server (https://apisecurityscan.net/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 3 SecurityScan tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
4,600+ MCP servers and 31,000+ tools scanned and risk-classified.