v1.0.0

New Akshare Stock.Bak2

BenignClawScan verdict for this skill. Analyzed May 1, 2026, 7:55 AM.

Analysis

This is a coherent A-share stock data helper using AkShare for public market data, with minor install/provenance and financial-guidance caveats.

GuidanceThis skill appears safe for public stock-data lookup and analysis. Before installing, use a trusted or pinned AkShare version, note the metadata mismatch, and do not treat generated buy/sell language as professional financial advice.

Findings (3)

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

The skill depends on a third-party Python package installed by the user without a pinned version. This is central to the stock-data purpose, but users should be aware of package provenance and version drift.

User impactThe behavior of the skill may depend on whichever AkShare version is installed at the time.

RecommendationInstall AkShare from a trusted package index and consider pinning a known-good version if using this in a sensitive workflow.

Agentic Supply Chain Vulnerabilities

SeverityInfoConfidenceHighStatusNote

metadata, _meta.json

Registry slug: new-akshare-stock-bak2; _meta.json slug: new-akshare-stock

The embedded metadata does not match the registry slug/owner information, suggesting the package may have been copied, renamed, or republished. No malicious runtime behavior is evidenced, but provenance is less clear.

User impactUsers may have less certainty about the package’s origin or whether it is the same artifact as the embedded metadata describes.

RecommendationConfirm the publisher and package identity before relying on it, especially if installing it into a production or financial-analysis environment.

Human-Agent Trust Exploitation

SeverityLowConfidenceHighStatusNote

analyze_600323.py

print("🟢 强烈建议买入 - 多个指标向好") ... print(f"   建议仓位：30-50%")

The script can produce strong investment-style recommendations, even though the skill also includes disclaimers that outputs are not investment advice.

User impactA user could over-trust generated buy/sell suggestions and make financial decisions based on simple technical indicators.

RecommendationTreat generated recommendations as educational or exploratory analysis only, and verify with independent research or a qualified financial professional.