Back to skill

Security audit

天天Skills

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward fund-screening connector that sends user-selected fund criteria to a disclosed 天天基金 API and does not show hidden persistence, local data harvesting, or destructive behavior.

Install only if you intend to use 天天基金's external fund-screening service. Your screening query parameters will be sent to that service using your TTFUND_APIKEY, and the results should be treated as informational rather than investment advice.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

External Transmission

Medium
Category
Data Exfiltration
Confidence
84% confidence
Finding

The skill instructs the agent to send requests to an external endpoint and include an API key in the X-API-Key header. While this is expected for a networked skill, it still creates a real data-exfiltration surface: user queries and screening parameters are transmitted off-platform to a third-party service, and broad triggers increase the risk of that happening without sufficiently explicit user intent.

Content

Scanner excerpt · SKILL.md (reported line 50)May include surrounding context.

  • skill_id 固定为 FUND_CONDITION_SELECT。
  • 其余筛选参数按用户问题按需补充,不要无关参数全部硬塞。

示例 curl

bash
curl --location 'https://skills.tiantianfunds.com/ai-smart-skill-service/openapi/skill/invoke' \

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The trigger examples are broad enough to match common financial-assistance requests such as '帮我调用 FUND_CONDITION_SELECT' or general fund-screening questions. This can cause the skill to activate in situations the user did not explicitly intend, increasing the chance of unnecessary external API calls and transmission of user-supplied financial query data to a third-party service.

Content

No source excerpt is available for this finding.