Ai Transcript Action Extractor

PassAudited by ClawScan on May 13, 2026.

Overview

This prompt-only skill appears benign and is scoped to extracting action items from user-pasted text while emphasizing redaction and manual verification.

This looks safe to install as a prompt-only productivity skill. Still, transcripts can contain confidential names, client details, HR/legal/medical/financial information, or proprietary material, so only paste text you are allowed to process and review the redaction and verification checklist before sharing results elsewhere.

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.

What this means

If the user chooses to copy transcript content into another AI service, they should redact private or regulated information first.

Why it was flagged

The skill may help prepare text for an external AI tool, but it clearly limits this to redacted, user-provided text and warns against sharing sensitive details.

Skill content
Before using or preparing text for any external AI tool: ... Redact confidential details before external AI use
Recommendation

Use the skill with pasted text you are allowed to process, and follow its redaction checklist before sharing any transcript with external tools.