Back to skill

Security audit

Orderly Positions Tpsl

Security checks for vulnerabilities and agentic risk

Overview

This skill is a trading helper whose actions match its purpose, but it should be reviewed because it includes live trading operations without clear safety guardrails.

Review this skill carefully before installing if it will be used with real Orderly credentials. Prefer sandbox or paper trading first, restrict API permissions where possible, and require explicit user confirmation before closing positions, changing leverage, placing TP/SL orders, stop orders, or canceling orders.

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
Vulnerability Patterns
  • Tool MisuseTool Parameter Abuse, Chaining Abuse, Unsafe Defaults
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (5)

Tool Parameter Abuse

High
Category
Tool Misuse
Confidence
80% confidence
Finding

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).

Content

Scanner excerpt · SKILL.md (reported line 383)May include surrounding context.

typescript
// Cancel single algo order
DELETE /v1/algo/order?order_id={order_id}&symbol={symbol}

// Cancel all algo orders for symbol
DELETE /v1/algo/orders?symbol={symbol}

Tool Parameter Abuse

High
Category
Tool Misuse
Confidence
80% confidence
Finding

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).

Content

Scanner excerpt · SKILL.md (reported line 386)May include surrounding context.

md
DELETE /v1/algo/order?order_id={order_id}&symbol={symbol}

// Cancel all algo orders for symbol
DELETE /v1/algo/orders?symbol={symbol}

// React SDK
const [algoOrders, { cancelAlgoOrder }] = useAlgoOrderStream();

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill gives concrete instructions and code for partially or fully closing positions through live trading endpoints, but it does not explicitly warn that these actions execute real trades and can irreversibly reduce or eliminate an open position. In a trading skill, omission of such warnings increases the chance that an agent or user will treat the examples as safe read-only operations and trigger financially harmful actions.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The leverage management section shows how to change leverage directly, but it lacks an explicit warning that increasing leverage materially raises liquidation risk and changes account-wide margin requirements. Because leverage changes can quickly make positions unsafe, presenting the action as a simple UI control without guardrails is dangerous in this financial context.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The TP/SL and algo-order sections provide direct order-placement examples against live endpoints but do not clearly state that these create active market-affecting orders tied to open positions. In practice, misconfigured trigger prices, sides, or quantities can unintentionally close positions, leave positions unprotected, or create unexpected execution behavior.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.