Back to skill

Security audit

ebfx-cli-skill

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent EBFX finance CLI helper, but it can trigger authenticated financial-data commands from broad, ambiguous user phrases.

Review before installing in environments where EBFX tokens or sender IDs are available. The skill should be limited to explicit EBFX requests, and agents should confirm intent before running authenticated dashboard, profit, or token-status commands from generic business questions.

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
  • 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The skill description and trigger guidance are broad enough to activate on common requests about data, quotes, profit, or logging in, which can cause the agent to invoke a sensitive finance CLI in situations where the user did not clearly request this tool. In this context, mistaken activation is more dangerous because the CLI accesses protected EBFX business data and may use ambient authentication tied to the current sender, increasing the risk of unnecessary exposure of operational or financial information.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The activation list contains ambiguous phrases like '查利润数据', '查 dashboard', and '登录系统' without boundaries, making over-triggering likely when users ask generic business questions. Because this skill is for a financial platform and explicitly encourages execution of authenticated CLI commands, false activations can lead to unintended access attempts, token-state probing, or disclosure of sensitive business metrics to the wrong conversational context.

Content

No source excerpt is available for this finding.