demo-production

AdvisoryAudited by Static analysis on May 13, 2026.

Overview

No suspicious patterns detected.

Findings (0)

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

The agent may create or modify project files to produce a runnable prototype before stopping for review.

Why it was flagged

The skill directs the agent to keep building before asking for review. This is central to the demo-building purpose and includes a review gate, but it means workspace changes may occur with limited interim prompting.

Skill content
Default behavior: autonomously continue until Stage 3, deliver an interactive demo, then stop for user review.
Recommendation

Use it in a branch or disposable workspace, give explicit constraints up front, and inspect the Stage 3 diff/demo before approving further work.

What this means

The resulting demo may be shaped by external sources, and careless use could accidentally copy inappropriate assets or adopt unsuitable patterns.

Why it was flagged

External references can influence workflows, architecture, or implementation ideas. This is disclosed and purpose-aligned, but web/GitHub content should be treated as untrusted input unless reviewed.

Skill content
The skill can trigger focused web or GitHub research when an idea resembles known products, open-source projects, or mature software categories.
Recommendation

Ask the agent to cite references, avoid copying protected assets or unreviewed code, and get approval before adding new dependencies.