Check if a skill has been certified as safe. Certification indicates the skill has been scanned, reviewed, and approved by a human administrator. Certified skills have a cryptographic hash that can be verified. Does not consume scan credits. Args: skill_url: The skill URL to check certification f...
Risk signalsAdmin/system-level operation
Part of the SecurityScan server.
Free to start. No card required.
AI agents call check_certification 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 check_certification 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": {
"check_certification": {}
}
}See the full SecurityScan policy for all 3 tools.
These attack patterns abuse exactly the kind of access check_certification 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.
Check if a skill has been certified as safe. Certification indicates the skill has been scanned, reviewed, and approved by a human administrator. Certified skills have a cryptographic hash that can be verified. Does not consume scan credits. Args: skill_url: The skill URL to check certification for Returns: CertificationResult indicating if the skill is certified, along with certification details if available. Example: check_certification("https://github.com/anthropics/anthropic-cookbook"). 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 check_certification: 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.
check_certification 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 check_certification 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 check_certification. 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.
check_certification 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.