Back to skill

Security audit

Datayes Stock Analysis

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed Chinese stock-analysis skill that gathers market and company data through named Datayes MCP tools and produces a report, without hidden code, persistence, or account-changing behavior.

Install this if you want Chinese-language stock research reports using Datayes MCP data. Review the resulting reports as informational analysis only, verify important figures independently, and do not treat the generated score or opinion as personalized 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
  • 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 (5)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The skill description and activation scope are broad enough that ordinary finance questions could trigger this workflow even when the user did not explicitly ask for a full stock-analysis skill. Over-broad triggering can cause inappropriate tool use, unexpected data access, and responses framed as investment analysis in contexts where a narrower or safer answer would be more appropriate.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The listed trigger examples include vague phrases such as asking whether a stock is worth buying, which are common user questions and may collide with ordinary conversational requests. In this skill context, that increases the chance of unintended activation and generation of high-stakes investment-style output without sufficient scoping, suitability checks, or clarification.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The entire skill file is written as a Chinese-only checklist and workflow, with no indication that users may choose another language or that the language restriction is intentional for a region-specific use case. Under the policy rules, a skill that effectively enforces a specific language without user opt-in is a natural-language policy concern.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
92% confidence
Finding

This markdown file contains user-facing natural-language guidance only in Chinese, and it does not state that the skill is China-specific or offer any language choice. Under the policy, forcing a specific language without user opt-in can be a locale/language policy violation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
95% confidence
Finding

The entire template is written as a prescriptive report format in Chinese, with no indication that users may choose another language or locale. Under the language/locale policy rule, forcing a specific language without user opt-in is a natural-language policy concern.

Content

No source excerpt is available for this finding.