Back to skill

Security audit

Market Sentiment

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent market-sentiment CSV analysis tool with disclosed local file input/output and no hidden network, persistence, or privilege behavior.

Installers should understand that this is a Chinese-first financial analysis helper. Use it only with CSV files you intend to analyze, choose any --output path deliberately, and treat its market scores and planner parameters as reference material 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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (10)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The skill description, examples, and operational guidance are written primarily in Chinese and present Chinese-language outputs as the default behavior, with no indication that users can select another language for normal operation. Under the language/locale policy, forcing a specific language without user opt-in is a natural-language policy concern.

Content

No source excerpt is available for this finding.

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
91% confidence
Finding

The skill documentation shows command examples that read from and write through local files, but it does not declare any explicit tool scope such as permissions or allowed-tools. That creates an authorization gap where an agent may infer filesystem access is expected without any user-visible restriction, increasing the chance of unintended local file access in a larger toolchain.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
77% confidence
Finding

Most of the skill’s operative description, feature names, model explanations, workflow text, and trigger phrases are presented only in Chinese, while English appears mainly in headings and disclaimers. This can functionally constrain usage to a specific language without an explicit opt-in or statement that other languages are supported.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The trigger list contains broad terms like 'sentiment', 'market context', and general market-state phrases that are likely to appear in ordinary financial discussion. Overbroad triggers can cause accidental invocation of this skill in contexts where the user did not request it, which may cascade into unnecessary file processing or downstream planner actions in the integrated workflow.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The description string is entirely in Chinese, and the topics also emphasize Chinese-language labels. Because this package metadata does not offer an alternate language or indicate that the skill is intentionally region-specific, it may violate language/locale policy by forcing a specific language without user opt-in.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
86% confidence
Finding

The comment states the implementation is in Chinese ('纯 Python 标准库实现,无外部依赖'), which indicates a language-specific constraint in natural language. Under the policy, forcing a specific language without offering user choice or documenting a justified locale constraint should be flagged.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

This Python file contains natural-language instructions, disclaimers, and subsequent user-facing messages exclusively in Chinese, which effectively forces a specific language for operation and interpretation. The policy explicitly calls out language or locale constraints as violations unless the skill offers user choice or clearly justifies the restriction.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

Command descriptions, reports, summaries, and error messages are emitted in Chinese only, so users cannot opt into another supported language. Because this is a general market-analysis tool rather than a clearly region-locked compliance utility, the fixed language behavior 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
87% confidence
Finding

This markdown file mixes English headings with Chinese-only changelog content, which can impose a language choice on users without opt-in. The policy specifically allows locale constraints only when they are explicitly documented and justified, which is not present here.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Low
Category
Not specified by scanner
Confidence
97% confidence
Finding

The README's strong-market example maps a clearly overheated market state ('超买/overbought') to stock-planner: --market bear, which is contradictory to the surrounding semantics and likely to propagate incorrect downstream behavior when users integrate via the provided shell pipeline. Because the skill is explicitly designed to feed planner_param into another tool, this documentation error can cause systematically wrong trading configuration and unsafe decision automation.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.