Security audit
Security checks for vulnerabilities and agentic risk
This trading skill is coherent but needs Review because it can access sensitive financial data and modify orders with broad triggers and incomplete confirmation guidance.
Review before installing. Use this only with an API key you intend to grant to the assistant, preferably one with the narrowest available permissions. Confirm every order and cancellation yourself, use read-only permissions if you only want monitoring, and avoid invoking it in shared or ambiguous conversations where account data could be exposed.
Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).
Request
Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).
Request
DELETE /orders/ORD-20250325-001
X-API-KEY: {X_TRADING_API_KEY}
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
The key is stored in the environment variable `X_TRADING_API_KEY`.
Base URL: `https://api.xtrading.com/v1`
> ⚠️ Never expose, log, or repeat the API key in any response.
> If `X_TRADING_API_KEY` is missing, ask the user to set it before proceeding.
The trigger phrases are broad enough to match generic account-related language such as 'balance', 'account', or 'portfolio', which can cause the trading skill to activate in contexts where the user did not clearly intend to access brokerage data. In a finance/trading skill, unintended invocation increases the chance of exposing sensitive financial information or initiating account-related workflows without sufficiently specific user intent.
This skill documentation covers retrieval of profile, balance, and positions data using an API key, which affects user financial privacy. The file does not include any warning or disclosure that invoking these endpoints accesses sensitive account information or that responses may contain personal and financial data.
The trigger phrases are broad enough to activate on ordinary conversation about 'history', 'report', 'transactions', or similar terms, which can cause the agent to load a skill that exposes sensitive trading and account-history functionality without clear user intent. In a financial context, unnecessary activation increases the chance of surfacing or querying private transaction records and expands the attack surface for prompt-routing mistakes or unintended data access.
This module handles highly sensitive financial records, including deposits, withdrawals, balances, and executed trades, but provides no user-facing warning or confirmation guidance before accessing or displaying that data. In the context of a trading skill, omission of sensitivity cues makes accidental disclosure more likely, especially in shared-device, delegated-assistant, or ambiguous-user-intent scenarios.
The trigger list includes broad generic terms such as "price" and "quote," which are common in many non-trading conversations and can cause unintended activation of this skill. In a trading context, accidental routing is more dangerous because it may expose market/account-adjacent functionality or lead users into financial workflows they did not intend to invoke.
The listed triggers include generic everyday words like "buy", "sell", "order", and "cancel", which are common in normal conversation and not narrowly scoped to trading actions. The file does not provide negative examples or contextual constraints to distinguish routine speech from explicit skill invocation.
No suspicious patterns detected.