Back to skill

Security audit

A Share Data

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent Chinese-language market-data skill with disclosed third-party finance data sources and no hidden code, persistence, or privilege escalation.

Before installing, use an isolated Python environment, consider pinning and reviewing dependency versions, and avoid using the skill for confidential watchlists or compliance-sensitive research unless the listed data providers are acceptable.

Vulnerability Patterns
  • Insecure DependenciesIntroduces malicious components through unsafe dependency sources
  • 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 (1)

T08 · Insecure Dependencies

Warning
Location
SKILL.md:148
Finding

Unpinned Third-Party Dependencies Installed Without Integrity Verification

Content
View full analysis

Vulnerability Details

File Location: SKILL.md, lines 148-152
Vulnerability Type: Unpinned and unverified third-party dependencies
Risk Level: Medium

Vulnerable Code Snippet:

markdown
## Installation

```bash
pip install akshare baostock yfinance
text

### Technical Analysis

The installation instructions retrieve the latest available versions of `akshare`, `baostock`, and `yfinance` without version constraints, cryptographic hashes, a lockfile, or an explicitly approved package index. Consequently, the installed artifacts can change after the skill has been audited.

Python packages can execute package-controlled code during installation and whenever imported. If a dependency release, transitive dependency, maintainer account, or configured package index is compromised, following this command could install attacker-controlled code. The project does not itself contain a malicious dependency or embedded payload; the issue is the absence of supply-chain controls around mutable external packages.

### Attack Path

1. An attacker compromises a named dependency, one of its transitive dependencies, its publishing account, or a package index used by the target environment.
2. The attacker publishes a malicious version that remains compatible with the unrestricted package names.
3. A user follows the documented `pip install` command.
4. `pip` resolves and installs the attacker-controlled release because no reviewed version or hash is required.
5. Malicious package code executes during installation or when the skill imports and uses the package.

### Impact Assessment

Successful exploitation could execute arbitrary Python code with the privileges of the account performing installation or running the skill. Depending on that account's permissions, this may expose accessible files, environment variables, API credentials, financial-query data, and network resources. It could also modify files or install 
...[truncated 232 chars]
Remediation
View remediation

Remediation Suggestions

  1. Pin every direct dependency to a reviewed exact version, for example with package==version.
  2. Generate a lockfile that also fixes all transitive dependency versions.
  3. Require cryptographic hashes during installation, such as through a hash-locked requirements file and pip install --require-hashes.
  4. Use an explicitly configured, trusted package index or an internally controlled package mirror.
  5. Scan dependency artifacts and review release provenance before updating pinned versions.
  6. Perform installation and execution in an isolated virtual environment or container under a non-administrative account.
  7. Establish a controlled update process in which dependency changes are reviewed, tested, and re-audited before deployment.
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The skill is written entirely in Chinese without offering a language choice or explicitly stating a locale restriction, which can cause users or orchestration agents to misunderstand behavior, data source usage, installation steps, and limitations. In a security-sensitive context, poor comprehensibility increases the chance that users miss important disclosures such as external network access, fallback behavior, or data-use constraints.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
91% confidence
Finding

The skill explicitly relies on multiple third-party market data providers and even documents direct fallback URLs, but it does not clearly warn users that requests and queried symbols may be sent to external services. This creates a transparency and privacy issue: users or downstream skills may assume the skill is a local 'pure data layer' while it actually transmits request metadata to several outside providers.

Content

No source excerpt is available for this finding.