Current Akshare List

ReviewAudited by ClawScan on May 10, 2026.

Overview

This skill mostly matches its stated stock-list purpose, but it asks the agent to create a recurring scheduled retry job, which is persistent behavior that should require clear user approval and cancellation controls.

Only use this skill if you are comfortable installing Akshare and making network calls to the data provider. Do not allow it to create a cron or scheduled retry job unless it first shows you the exact job, retry limit, output path, and how to cancel it.

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.

What this means

The agent could leave a scheduled job running and repeatedly make network/API requests for hours after the original task.

Why it was flagged

The skill instructs creation of a recurring background retry task that can continue after the initial interaction. Although it is disclosed and capped, the artifact does not clearly require explicit user approval, show where the task is installed, or provide a clear cancellation path.

Skill content
自动建立定时任务重试直到接通 ... 创建 cron 任务,每30分钟重试东财接口 ... 保留任务继续重试 ... 最大重试次数:24次(12小时)
Recommendation

Require explicit user confirmation before creating any scheduled task, show the exact schedule and command/payload, store it in a clearly named location, and provide a simple cancellation/removal command.

What this means

Installing an unpinned package may produce different behavior over time depending on the package version available when installed.

Why it was flagged

The skill depends on installing the external Akshare package, but the provided install metadata has no install spec or pinned package version. This is expected for the skill's purpose but leaves package provenance/version control to the user.

Skill content
akshare SDK:`pip install akshare`
Recommendation

Use a pinned Akshare version and document the expected package source before running the script.