Security audit

A Share Analysis

Security checks for vulnerabilities and agentic risk

Overview

This is a plain Markdown skill for structured A-share stock analysis, with expected web research and no hidden code, persistence, credential use, or account-changing behavior.

Install only if you want an A-share analysis assistant. Treat outputs as educational research, not investment advice, and avoid providing sensitive cost basis, position size, or portfolio details unless you are comfortable with the agent using that context during web-backed research.

A.I.G

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

SkillSpector

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (3)

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 90% confidence
Finding: The skill describes itself as the '唯一分析层' and presents a broad stock-analysis workflow without clear invocation boundaries, eligibility checks, or scoping constraints. Overly broad positioning can cause the agent to activate this skill in ambiguous contexts and produce high-stakes financial analysis outside intended conditions, increasing the chance of inappropriate tool use and unsafe financial guidance.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The workflow explicitly instructs the agent to use web_search and web_fetch for supplemental research, but the skill does not clearly warn users that external network access may occur or that prompts, tickers, or other contextual data may be sent to third-party sources. This creates privacy, compliance, and provenance risks, especially in a financial-analysis context where user portfolio details or watchlists may be sensitive.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 84% confidence
Finding: The skill description and instructions are entirely in Chinese and centered on 'A股' analysis, but there is no statement that the skill supports only Chinese output or that users may choose another language. This can constitute a language/locale policy issue when the skill implicitly forces one language without opt-in.
Content: No source excerpt is available for this finding.