Adversarial Prompting

PassAudited by ClawScan on May 10, 2026.

Overview

This skill is a coherent analysis helper, with the main thing to notice being that it automatically saves the generated analysis as a local markdown file.

This appears safe for normal use as an analysis workflow. Before installing, be aware that it is designed to save the completed analysis to a markdown file in your home directory; avoid using it with sensitive details unless you are comfortable with that local record.

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.

What this means

Using the skill may create a local markdown file as part of normal operation.

Why it was flagged

This directs the agent to run an included helper script after use. The behavior is disclosed and purpose-aligned, but it is automatic rather than separately confirmed.

Skill content
After presenting the analysis, automatically export the complete output to a markdown file using `scripts/export_analysis.py`.
Recommendation

If you do not want local files created, tell the agent not to run the export step or delete the generated file afterward.

What this means

If the analysis includes private business details, personal information, or secrets, those details may remain in a local file.

Why it was flagged

The helper saves the complete analysis content to a markdown file in the user's home directory, creating a persistent local record.

Skill content
filepath = Path.home() / filename ... f.write(content)
Recommendation

Avoid including sensitive information unless you are comfortable storing it locally, and remove the generated markdown file when it is no longer needed.