Back to skill
Skillv1.0.0

ClawScan security

伐谋 - 数据分析工具 · ClawHub's context-aware review of the artifact, metadata, and declared behavior.

Scanner verdict

BenignMar 13, 2026, 6:11 AM
Verdict
benign
Confidence
high
Model
gpt-5-mini
Summary
The skill is an instruction-only data-analysis helper whose requirements and runtime instructions align with its stated purpose and do not request unexpected credentials or install steps.
Guidance
This skill is coherent for dataset analysis: it doesn't ask for credentials or install code. Before enabling, confirm that your agent environment uses the referenced paths (/mnt/user-data/uploads/ and /mnt/user-data/outputs/) and that you are comfortable the agent can read uploaded files placed there. Also note the skill declares it should be invoked whenever a user mentions data-analysis terms — consider whether you want it auto-triggered in all those cases. Finally, as with any data-processing tool, avoid uploading sensitive data unless you trust the agent/environment's storage and retention policies.

Review Dimensions

Purpose & Capability
okName/description (数据分析) matches the instructions: guidance on understanding, cleaning, transforming, and reporting on datasets. No unrelated credentials, binaries, or installs are requested.
Instruction Scope
noteInstructions stay within data-analysis tasks (quality checks, cleaning rules, reporting format). It explicitly references local upload/output paths (/mnt/user-data/uploads/ and /mnt/user-data/outputs/) and runtime settings (encoding, matplotlib fonts), which is reasonable for a data skill but worth noting because the skill assumes access to those filesystem locations and will be triggered whenever the user mentions data analysis.
Install Mechanism
okNo install spec and no code files — instruction-only skill. This minimizes on-disk footprint and external downloads.
Credentials
okRequires no environment variables, credentials, or config paths. The only environment assumptions are file locations and common encoding/font settings needed for data processing and visualization.
Persistence & Privilege
okalways is false and the skill does not request persistent system modifications or elevated privileges. Autonomous invocation is allowed by platform default but not combined with other high-risk factors.