ClawHub
Back to skill

Security audit

A股技术分析工具包

Security checks for vulnerabilities and agentic risk

Overview

This A-share analysis skill appears security-benign, though it overstates some advertised analysis features and is Chinese-only.

Install only if you are comfortable with a lightweight, local Chinese-language technical-analysis helper. Treat outputs as informational only, verify market data and formulas independently, and do not rely on the advertised unsupported features unless the publisher adds them.

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
  • 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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Tp4

High
Category
MCP Tool Poisoning
Confidence
91% confidence
Finding

The code largely fits the general theme of A-share technical analysis, but the declared description materially overstates the implemented feature set. Actual functions are limited to MACD, KDJ, RSI, a basic support/resistance heuristic, and formatted report generation. Several specifically advertised capabilities—K线形态识别, 均线系统, 布林带, and 资金流向解读—are absent from the supplied code. There are no suspicious undeclared behaviors, permissions, network access, or unrelated triggers; the mismatch is that the description promises substantially more analytical functionality than the code actually provides.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
91% confidence
Finding

This Python file contains user-facing natural-language strings exclusively in Chinese, including the module description, docstrings, signal labels, and generated report text. Under the language/locale policy rule, forcing a specific language without user opt-in can be a policy violation when no alternative language selection is provided.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.