Back to skill

Security audit

Eastmoney Stock.Bak2

Security checks for vulnerabilities and agentic risk

Overview

This stock skill does not show host takeover behavior, but it should be reviewed because it misstates data sources and includes stale or prescriptive financial outputs that could mislead users.

Review this before installing if you rely on accurate financial data. The skill should clearly disclose whether it uses Eastmoney or Sina, remove or label hardcoded and fixed-date outputs, avoid prescriptive investment advice unless explicitly scoped for that use, and use HTTPS for market-data requests. Do not treat its outputs as verified live market data or investment advice without independent confirmation.

Vulnerability Patterns
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • 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
Findings (2)

T09 · Insecure Skill Coding Practices

Warning
Location
sector_rank.py:12
Finding

Sector Ranking Data Retrieved over Unencrypted HTTP

Content
View full analysis
Remediation
View remediation

T09 · Insecure Skill Coding Practices

Warning
Location
scripts/sector_rank.py:19
Finding

Sector Ranking API Uses Plaintext Transport in Packaged Script

Content
View full analysis
Remediation
View remediation
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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
Findings (24)

Tp4

High
Category
MCP Tool Poisoning
Confidence
97% confidence
Finding

Claiming support for Eastmoney quote fields like price change and volume while not actually retrieving or presenting them, and instead using a fixed test script, is deceptive behavior. In a stock-analysis setting, inaccurate claims about data freshness, source, and completeness can mislead users and downstream systems that rely on the skill's advertised capabilities.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
95% confidence
Finding

Claiming support for Eastmoney quote fields like price change and volume while not actually retrieving or presenting them, and instead using a fixed test script, is deceptive behavior. In a stock-analysis setting, inaccurate claims about data freshness, source, and completeness can mislead users and downstream systems that rely on the skill's advertised capabilities.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

Claiming support for Eastmoney quote fields like price change and volume while not actually retrieving or presenting them, and instead using a fixed test script, is deceptive behavior. In a stock-analysis setting, inaccurate claims about data freshness, source, and completeness can mislead users and downstream systems that rely on the skill's advertised capabilities.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
96% confidence
Finding

Claiming support for Eastmoney quote fields like price change and volume while not actually retrieving or presenting them, and instead using a fixed test script, is deceptive behavior. In a stock-analysis setting, inaccurate claims about data freshness, source, and completeness can mislead users and downstream systems that rely on the skill's advertised capabilities.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
95% confidence
Finding

Claiming support for Eastmoney quote fields like price change and volume while not actually retrieving or presenting them, and instead using a fixed test script, is deceptive behavior. In a stock-analysis setting, inaccurate claims about data freshness, source, and completeness can mislead users and downstream systems that rely on the skill's advertised capabilities.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
95% confidence
Finding

Claiming support for Eastmoney quote fields like price change and volume while not actually retrieving or presenting them, and instead using a fixed test script, is deceptive behavior. In a stock-analysis setting, inaccurate claims about data freshness, source, and completeness can mislead users and downstream systems that rely on the skill's advertised capabilities.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
95% confidence
Finding

Claiming support for Eastmoney quote fields like price change and volume while not actually retrieving or presenting them, and instead using a fixed test script, is deceptive behavior. In a stock-analysis setting, inaccurate claims about data freshness, source, and completeness can mislead users and downstream systems that rely on the skill's advertised capabilities.

Content

No source excerpt is available for this finding.

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
94% confidence
Finding

The skill declares that it fetches external stock data, but it does not specify any tool scope such as allowed network access. Missing explicit permissions weakens reviewability and containment, and can let a skill use broader network capabilities than users or operators expect.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The skill metadata says it queries Eastmoney stock data, but the implementation actually sends requests to Sina Finance. This is a supply-chain/integrity issue: users and downstream agents may trust the provenance, licensing, format, or reliability of Eastmoney data while receiving data from a different provider, which can lead to incorrect decisions, policy violations, or unexpected dependencies.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill is described as providing stock data, but it also produces prescriptive trading guidance such as whether to buy, hold, avoid chasing gains, or avoid bottom-fishing. In a finance context, this expands the skill from factual retrieval into advisory behavior without any suitability checks, risk profiling, or explicit authorization, which can mislead users and create harmful or non-compliant financial recommendations.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
98% confidence
Finding

The docstring states the script uses the Sina Finance API, but no API call is made at all. This creates source misrepresentation and can mislead users or downstream agents about the provenance, freshness, and trustworthiness of financial information.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

This code presents its title, headings, stock guidance, and risk notices entirely in Chinese, with no indication that the user can select another language or that the skill is intentionally limited to a Chinese-language audience. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill advertises Eastmoney stock-data querying but instead returns hardcoded sector and stock picks. In a financial context, this is dangerous because users may rely on stale, fabricated, or misleading market information while believing it is live data from a trusted source.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The docstring, all user-facing print output, and the investment guidance are entirely in Chinese, with no indication that the user can choose another language or locale. The policy explicitly calls out language or locale constraints as violations when they are imposed without user opt-in.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
98% confidence
Finding

The skill metadata says it queries Eastmoney stock data, but this file instead emits hard-coded market commentary, sector rankings, and stock picks dated to a fixed day. That mismatch can mislead downstream users or agents into trusting stale or fabricated information as live market data, which is especially risky in a financial context.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

This section goes beyond answering stock data questions and gives explicit portfolio allocation, stock selection, position sizing, and stop-loss guidance. In a financial skill, unauthorized investment advice can materially influence user decisions while appearing tool-endorsed, creating risk of financial harm and trust abuse.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The skill metadata says it provides Eastmoney stock data, but the implementation actually calls Sina Finance. This is a supply-chain and trust/integrity issue: users or downstream agents may rely on a specific data source for accuracy, licensing, or compliance reasons and unknowingly receive data from a different provider.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The code claims to support Hong Kong and U.S. stocks, but the parsing and market-handling logic is clearly tailored to the Sina A-share response layout. This can cause incorrect parsing, misleading outputs, or silent failures for non-A-share symbols, which is dangerous in a financial-data skill because users may act on inaccurate market information.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

All user-facing text, including the module description, status messages, headings, and guidance, is fixed in Chinese. This imposes a specific language/locale on all users without opt-in or an alternative, which matches the language-policy violation criteria.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill’s stated purpose is stock-data querying, but this code goes further by printing concrete operational suggestions such as following hot sectors, choosing leading stocks, setting stop-losses, and position control. In a finance context, embedding prescriptive investment guidance can mislead users into treating generated output as advice, increasing regulatory, trust, and user-harm risk if the guidance is wrong or inappropriately generalized.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
98% confidence
Finding

The code claims to implement an Eastmoney stock skill, but actually sends requests to Sina Finance. This creates a supply-chain/integrity problem: users and higher-level agents may make trust, compliance, or data provenance decisions based on the manifest, while the runtime behavior uses a different provider with different terms, availability, and data characteristics. In an agent setting, this mismatch can also bypass allowlists or policy controls that were scoped only to Eastmoney.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
89% confidence
Finding

The package description is written only in Chinese ("东方财富股票数据查询"), which indicates a fixed language choice without offering any user language or locale option. Under the policy, language constraints should be opt-in or clearly justified as region-specific.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
90% confidence
Finding

The code makes outbound network requests to a third-party market-data API without any user-visible disclosure that data is being fetched remotely. This is a transparency and privacy concern because users may not realize their queries or usage context depend on external transmission, though the snippet does not appear to send sensitive user-provided data directly.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
92% confidence
Finding

The file's natural-language strings and docstrings are entirely in Chinese, including the purpose description and user-facing output text, with no indication that the skill is intentionally limited to Chinese-speaking users or a China-specific deployment context. Under the policy, forcing a specific language without user opt-in is a natural-language locale violation.

Content

No source excerpt is available for this finding.