Ai Workflow Red Team Lite

PassAudited by ClawScan on May 1, 2026.

Overview

This appears to be a local, defensive AI-workflow red-team reporting skill with no evidence of credential use, networking, persistence, or destructive behavior.

This skill looks suitable for defensive review use. Before installing, note that its optional helper is a local Python script that processes files you provide and may write a report, so avoid feeding unnecessary personal or confidential data and review the chosen input and output paths.

Findings (1)

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.

Low

#ASI05: Unexpected Code Execution

What this means

If used, the helper can read the input file you provide and create a report file at the output path you choose.

Why it was flagged

The skill may invoke a bundled local Python helper and write an output file. This is clearly disclosed and aligned with generating structured red-team review reports, but it is still local code execution.

Skill content

如运行环境允许 shell / exec，可使用：
   - `python3 "{baseDir}/scripts/run.py" --input <输入文件> --output <输出文件>`

Recommendation

Run it only on intended files, choose a safe output location, and use the documented dry-run or stdout behavior if you do not want a file written.