v1.0.0

pinyin-box

BenignClawScan verdict for this skill. Analyzed May 1, 2026, 7:54 AM.

Analysis

The skill’s behavior matches its stated purpose of generating Chinese writing-practice sheets, but it requires trusting an external Python package installation.

GuidanceThis skill appears appropriate for making pinyin or handwriting-practice sheets. Before installing, make sure you trust the external pinyin-box package source, and avoid giving it private text or images unless you are comfortable using them for OCR and generated output files.

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

requirements.txt

pinyin-box>=1.0.0
https://github.com/yanglinzhen/pinyin-box/releases/download/v1.0.0/pinyin_box-1.0.0-py3-none-any.whl

The dependency setup uses an unpinned version range and a direct remote wheel URL, so installation depends on trusting that external package source; this is central to the skill’s purpose and is disclosed.

User impactInstalling the dependency runs third-party package code in the user environment before the skill can generate practice sheets.

RecommendationInstall only if you trust the package source, and prefer a pinned, hash-verified dependency or reviewed install specification.

Tool Misuse and Exploitation

SeverityInfoConfidenceMediumStatusNote

SKILL.md

pinyin-box -t "文本内容" -s medium -o ~/.openclaw/workspace/pinyin-box/output/pinyin_img1.png

The skill demonstrates passing text content into a CLI command; this is expected for the conversion task, but user text should be handled as data rather than unsafely interpolated into a shell string.

User impactUnusual characters in user-provided text could cause command errors or unsafe behavior if an agent builds shell commands without proper escaping.

RecommendationPass user text with safe argument handling or through a temporary input file, and keep output paths scoped to the workspace.