Back to skill
Skillv1.0.0

ClawScan security

Txt Col Align · ClawHub's context-aware review of the artifact, metadata, and declared behavior.

Scanner verdict

BenignApr 16, 2026, 9:45 AM
Verdict
benign
Confidence
high
Model
gpt-5-mini
Summary
The skill's code and instructions match its stated purpose (aligning delimiter-separated text); it does not request credentials, perform network I/O, or install additional software.
Guidance
This skill appears to do exactly what it claims: format delimiter-separated text for readability. Consider that the source/homepage is unknown — if you plan to install/use it beyond running the included script, inspect or run tool.py locally to confirm behavior. Because it's a plain script, installation typically means saving the file and making it executable; no secrets or network access are needed. If you require a packaged/official tool, prefer a version from a known repository or source.

Review Dimensions

Purpose & Capability
okName/description (align text table columns) align with the provided code: tool.py reads stdin or a file, detects a delimiter, computes column widths, and prints aligned text. No unrelated capabilities (cloud access, secrets, network) are present.
Instruction Scope
okSKILL.md examples and usage stay within the stated purpose (running the CLI on files or piped input). The runtime instructions do not ask the agent to read other files, environment variables, or send data externally. Minor editorial mismatches: examples/epilog in tool.py use 'colalign' while SKILL.md uses 'txt_col_align', but this is a cosmetic inconsistency, not a security concern.
Install Mechanism
okThere is no install spec (instruction-only skill) and the shipped tool.py is a simple standalone script; nothing is downloaded from external URLs or extracted to disk during install.
Credentials
okThe skill declares no required environment variables, credentials, or config paths and the code does not read environment variables or secret files.
Persistence & Privilege
okSkill is not always-enabled and does not modify other skills or global agent config. It runs only when invoked and requires no elevated privileges.