High-risk tools in Agent Vending Factory
5 of the 6 tools in Agent Vending Factory are classified as high risk. This page profiles those tools specifically, with recommended policy actions and the attack patterns that target them.
Every operation listed below is an action PolicyLayer recommends controlling at the transport layer. Open any tool to see the full profile, risk score, and YAML policy snippet.
Tools at high risk
-
agent_exampleExecutePOST /agents/agent_example/run — Single-turn Claude Sonnet inference endpoint. Input: {question: string, max_tokens: integer (default 1024)}. Output: {success, answer, usage: {i...
-
tool_compute_sandboxExecutePOST /tools/tool_compute_sandbox/run — Executes Python 3.12 code in an isolated subprocess with a 5-second hard timeout. Input: {python_code: string, input_data: any (optional, ...
-
tool_exampleExecutePOST /tools/tool_example/run — Stateless text utility for testing x402 payment flows. Input: {text: string}. Output: {original, uppercase, word_count, char_count}. Cost: $0.0010...
-
tool_sa_airport_oracleExecutePOST /tools/sa-airport-oracle/run — Returns live flight status from ACSA (airports.co.za). Input: {airport_code: 'JNB'|'CPT'|'DUR', flight_number: string, request_type: 'arrival...
-
tool_zar_pricesExecutePOST /tools/zar-prices/run — Returns live bid/ask/last prices for crypto/ZAR pairs. Input: {pair: 'BTC/ZAR'|'ETH/ZAR'|'SOL/ZAR'|'USDC/ZAR'|'all'}. Output: array of {exchange, pa...
Attacks that target this class
High-risk tools in any server share these documented attack patterns. Each links to the full case and the defensive policy.