v0.1.0

Akshare Skill

BenignClawScan verdict for this skill. Analyzed May 1, 2026, 7:04 AM.

Analysis

This is a documentation-only AKShare guide; the main thing to notice is that it asks users to install third-party Python packages and fetch public financial data from the internet.

GuidanceBefore installing, verify the AKShare and pandas packages, use a virtual environment, and consider pinning versions. Expect the skill to use local Python and internet access to retrieve financial data; the supplied artifacts do not request credentials or show account-changing behavior.

Findings (2)

Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.

Abnormal behavior control

Checks for instructions or behavior that redirect the agent, misuse tools, execute unexpected code, cascade across systems, exploit user trust, or continue outside the intended task.

Agentic Supply Chain Vulnerabilities

SeverityLowConfidenceHighStatusNote

SKILL.md

pip install akshare pandas

The skill asks the user to install external Python packages without version pinning. This is expected for an AKShare helper, but package provenance and version changes matter.

User impactInstalling third-party Python packages can add code to the user's local environment; a compromised or unexpectedly changed package version could affect the system or analysis results.

RecommendationInstall in a virtual environment, verify the AKShare and pandas package sources, and pin versions if reproducibility or supply-chain control is important.

Tool Misuse and Exploitation

SeverityInfoConfidenceHighStatusNote

SKILL.md

在用户本地运行 Python 代码，实时从网络采集数据到本地

The skill discloses that AKShare runs local Python code to collect data from online sources. This is coherent with the purpose, but users should expect internet access and local data output.

User impactUsing the skill may cause the local machine to make requests to financial-data websites and save retrieved data locally.

RecommendationUse it only for intended financial-data queries, review requested data ranges, and follow the relevant data-source terms and rate limits.