Get detailed information about a known agent attack class. Arc Security has documented 22 distinct attack classes from real-world ClawHub skill audits. Each class includes OWASP Agentic AI Top 10 mapping. Args: attack_class: The attack class to look up (e.g., 'soul_engineering', 'crypto_drain', '...
Part of the Arc Security server.
Free to start. No card required.
AI agents call get_attack_class_info to retrieve information from Arc Security 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 get_attack_class_info 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": {
"get_attack_class_info": {}
}
}See the full Arc Security policy for all 14 tools.
These attack patterns abuse exactly the kind of access get_attack_class_info 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.
Get detailed information about a known agent attack class. Arc Security has documented 22 distinct attack classes from real-world ClawHub skill audits. Each class includes OWASP Agentic AI Top 10 mapping. Args: attack_class: The attack class to look up (e.g., 'soul_engineering', 'crypto_drain', 'anti_safety_training'). Use list_attack_classes to see all options.. It is categorised as a Read tool in the Arc Security MCP Server, which means it retrieves data without modifying state.
Register the Arc Security MCP server in PolicyLayer and add a rule for get_attack_class_info: 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 Arc Security. Nothing to install.
get_attack_class_info 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 get_attack_class_info 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 get_attack_class_info. 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.
get_attack_class_info is provided by the Arc Security MCP server (arc-security-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 14 Arc Security 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.