Back to skill
Skillv1.0.0

ClawScan security

ACG-Rust 教学工具 · ClawHub's context-aware review of the artifact, metadata, and declared behavior.

Scanner verdict

BenignMar 2, 2026, 3:43 PM
Verdict
benign
Confidence
high
Model
gpt-5-mini
Summary
The skill is a self-contained, local Python teaching tool whose required files, runtime instructions, and requested capabilities align with its stated purpose.
Guidance
This skill appears coherent and self-contained: it runs a local Python script that presents static teaching content and keeps progress in memory. If you plan to install it: (1) review the bundled scripts (already done) and confirm no network calls or hidden execs—this script has none; (2) run it in a sandbox or isolated environment if you prefer extra caution; (3) be aware the SKILL.md example uses a hardcoded workspace path—ensure the path matches where the skill is installed; (4) because the code is bundled, also check updates from the skill author before trusting future versions. Overall the footprint is small and proportional to an educational tool.

Review Dimensions

Purpose & Capability
okName/description (ACG-themed Rust ownership teacher) match the included files: a SKILL.md, two reference docs, and a single Python script implementing teaching functions. The only declared runtime dependency is python3, which is appropriate and proportional.
Instruction Scope
noteSKILL.md instructs running the included Python script from the agent workspace (hardcoded example path ~/.openclaw/workspace/skills/acg-rust-teacher/scripts/acg-rust-teacher.py). Instructions remain within the educational scope and do not request reading unrelated files or external secrets. Note: the path assumption is workspace-specific and brittle but not malicious.
Install Mechanism
okThere is no external installer or network download. The SKILL.md references installing the provided local file (scripts/acg-rust-teacher.py). All code is bundled with the skill—no third-party packages or remote URLs are involved.
Credentials
okThe skill declares no required environment variables, credentials, or config paths. The Python code does not read environment variables or external secrets and uses only standard-library imports. Requested privileges are proportionate to the stated functionality.
Persistence & Privilege
okalways is false and default autonomous invocation is allowed (normal). The skill does not modify other skills or system configuration. Learning progress is tracked in-memory in the Python object (no persistent storage or external transmission).