Back to skill

Security audit

天天Skills

Security checks for vulnerabilities and agentic risk

Overview

This skill is a read-only Tiantian Fund information lookup that uses a user-configured API key to call its disclosed remote service.

Install only if you intend to use Tiantian Fund's API service. Treat TTFUND_APIKEY as a secret: the skill will use it for requests to skills.tiantianfunds.com, so avoid sharing logs or command output that might reveal the key.

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 (4)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill instructs the agent to read a local API key and transmit it to a remote endpoint, but it does not clearly warn the user that a local secret will be used and sent off-device. This weakens informed consent and can surprise users into authorizing third-party access with credentials they did not expect the skill to consume.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
92% confidence
Finding

The skill explicitly directs transmission of user-supplied fund query data and a locally sourced API key to an external domain. External transmission is expected for this integration, but it remains security-relevant because it creates a data egress path and exposes a local secret to a remote service if invoked unintentionally or without clear consent.

Content

Scanner excerpt · SKILL.md (reported line 33)May include surrounding context.

bash
curl --location 'https://skills.tiantianfunds.com/ai-smart-skill-service/openapi/skill/invoke' \
--header "X-API-Key: $TTFUND_APIKEY" \
--header 'Content-Type: application/json' \
--data '{

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The example trigger phrases are broad enough to overlap with ordinary user requests, which can cause the skill to activate unintentionally. In a skill that sends requests to an external service and may use a locally stored API key, accidental invocation increases the chance of unintended data transmission or credential-backed actions.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

技能名称与全文说明均默认使用中文语境和中文平台路径,但未说明这是面向特定中文用户群体的区域化技能,也未给出语言选择或适用范围。按照自然语言政策检查,这构成了默认强制特定语言/locale 的倾向。

Content

No source excerpt is available for this finding.