A股技术分析报告

• Outcome: Pass
• Latest audit: Sep 16, 2026 · 6:13 AM UTC
• Version: 1.0.0

Overview

This is a straightforward Chinese A-share stock analysis helper, with the main caution that some market data URLs use insecure HTTP and could affect report accuracy.

Install only if you are comfortable with a Chinese-language A-share workflow that fetches public Eastmoney data. Treat generated reports as informational, verify important numbers independently, and do not rely on it as investment advice.

A.I.G

Vulnerability Patterns

• Insecure Skill Coding Practices: Finds exploitable flaws such as hardcoded secrets or command injection
• Skill Instruction Hijacking: Alters the agent's session goals or safety constraints when the skill loads
• Agent Memory Poisoning: Writes attacker-controlled rules into memory that affect later sessions
• Remote Payload Retrieval and Execution: Fetches external code whose behavior can change after review
• Embedded Malicious Code: Ships malicious scripts inside the skill and executes them locally

Findings (1)

T09 · Insecure Skill Coding Practices

Warning

• Location: SKILL.md:26

Finding

Unauthenticated HTTP Transport for Financial Market Data

Content

View full analysis

Vulnerability Details

File Location: SKILL.md:26,36-37; duplicate instructions in a-stock-technical-analysis/SKILL.md:26,36-37
Vulnerability Type: T09: Insecure Skill Coding Practices
Risk Level: Medium

Vulnerable code in SKILL.md:

text

http://push2.eastmoney.com/api/qt/stock/get?secid=0.{代码}&fields=f43,f44,f45,f46,f47,f48,f57,f58,f60,f170,f171

text

http://push2.eastmoney.com/api/qt/stock/get?secid=1.000001&fields=f43,f57,f58,f60
http://push2.eastmoney.com/api/qt/stock/get?secid=0.399001&fields=f43,f57,f58,f60

The same vulnerable endpoints appear at the corresponding lines in a-stock-technical-analysis/SKILL.md.

Technical Analysis

The Skill directs the Agent to retrieve stock and index information through plaintext HTTP. HTTP does not provide transport encryption, server authentication, or response-integrity protection. An attacker capable of observing or modifying network traffic—such as a malicious access point, compromised proxy, or hostile network intermediary—could intercept these requests and replace the returned market values.

The affected responses supply decision-relevant fields used to generate technical-analysis conclusions. Manipulating prices, daily highs and lows, previous closes, trading volumes, or index values could consequently corrupt trend comparisons, support and resistance levels, valuation commentary, and risk assessments.

No credentials or private user information are shown as being transmitted through these endpoints. The issue concerns the integrity and authenticity of public financial data rather than confidentiality or direct system compromise.

Attack Path

1. A user invokes the Skill to analyze an A-share security.
2. The Agent requests stock or index data from one of the documented http://push2.eastmoney.com endpoints.
3. An attacker with a network interception position captures the plaintext HTTP request.
4. The attacker returns a forged or modified API response containin ...[truncated 767 chars]

Remediation

View remediation

Remediation Suggestions

1. Replace every http://push2.eastmoney.com URL with a verified https:// endpoint supported by the provider.
2. Reject redirects that downgrade requests from HTTPS to HTTP.
3. Treat browser-page and API content as untrusted input, and validate response structure, expected field types, stock identifiers, and reasonable numeric ranges before generating analysis.
4. Cross-check decision-critical values against an independent HTTPS-protected source or the HTTPS Eastmoney browser snapshot.
5. Validate interpolated stock codes with a strict allowlist pattern such as ^[0-9]{6}$ before constructing URLs.
6. If secure transport or validation fails, stop using the affected values and explicitly report that trustworthy data is unavailable rather than producing conclusions from unverified input.
7. Apply the same corrections to both duplicated Skill files to prevent the insecure instructions from remaining active in one copy.

SkillSpector

Vulnerability Patterns

• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (2)

Natural-Language Policy Violations

Medium

• Category: Not specified by scanner
• Confidence: 91% confidence

Finding

The entire report template is written as mandatory Chinese output, and there is no indication that users may choose another language or that the skill is limited to a China-specific locale by policy. Under the language/locale policy rule, this is a natural-language policy concern because it imposes a specific language without explicit user opt-in.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

• Category: Not specified by scanner
• Confidence: 87% confidence

Finding

The entire report template is written to produce output in Chinese and does not indicate that the user can choose another language. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation unless the locale constraint is explicitly documented and justified.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.