Back to skill

Security audit

天枢短剧爆款因子分析报告

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Chinese short-drama analysis service with an external API and optional Alipay payment flow, and I found no hidden code, persistence, or deceptive behavior.

Install only if you are comfortable sending short-drama titles or keywords to sinodata.io and using a China-focused Alipay payment flow for full reports. Payment is disclosed as 9.90 CNY per full report, and users should confirm they want the paid report before following the payment link.

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 (4)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger description is broad enough to activate on generic requests about analysis, evaluation, or why something is successful, which can cause the wrong skill to be invoked outside its intended short-drama niche. Over-broad routing can lead to confused-deputy behavior, unexpected external API/payment flows, and reduced user control over which capability is being used.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The trigger list is broad enough to match many ordinary conversations about short dramas, script analysis, recommendations, and trending content. This can cause the skill to activate in contexts where the user did not explicitly request this paid external analysis service, increasing the risk of unwanted routing, accidental third-party data disclosure, and inappropriate payment prompts.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
91% confidence
Finding

The description states "仅限国内用户", which imposes a locale/region restriction in natural language. The file does not offer user opt-in or choice, and the restriction is not explained as a compliance or legal requirement.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
74% confidence
Finding

The manifest description is entirely in Chinese and pricing is denominated only in CNY/Alipay, which suggests the skill may be limited to a Chinese-language and China-specific locale experience. There is no natural-language statement offering users a language choice or explicitly documenting that the skill is intentionally region-specific.

Content

No source excerpt is available for this finding.