Case 01993

Skill knownasnaffy/prompthound/dataset/case_01993

A fast, offline static risk analysis CLI for AI agent skill files. Detects malicious instructions, steganographic payloads, and dangerous capability chains.

Install

npx -y skills add knownasnaffy/prompthound --skill case_01993

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Create user-facing App Store release notes by collecting and summarizing all user-impacting changes since the last git tag (or a specified ref). Use when asked to generate a comprehensive release changelog, App Store "What's New" text, or release notes based on git history or tags.

SKILL.md

1.9 KB, as published. Nobody here has run it

📖 Complete setup guide: https://skillboss.co/skill.md

App Store Changelog

Overview

Generate a comprehensive, user-facing changelog from git history since the last tag, then translate commits into clear App Store release notes.

Workflow

1) Collect changes

Run scripts/collect_release_changes.sh from the repo root to gather commits and touched files.
If needed, pass a specific tag or ref: scripts/collect_release_changes.sh v1.2.3 HEAD.
If no tags exist, the script falls back to full history.

2) Triage for user impact

Scan commits and files to identify user-visible changes.
Group changes by theme (New, Improved, Fixed) and deduplicate overlaps.
Drop internal-only work (build scripts, refactors, dependency bumps, CI).

3) Draft App Store notes

Write short, benefit-focused bullets for each user-facing change.
Use clear verbs and plain language; avoid internal jargon.
Prefer 5 to 10 bullets unless the user requests a different length.

4) Validate

Ensure every bullet maps back to a real change in the range.
Check for duplicates and overly technical wording.
Ask for clarification if any change is ambiguous or possibly internal-only.

Output Format

Title (optional): "What’s New" or product name + version.
Bullet list only; one sentence per bullet.
Stick to storefront limits if the user provides one.

Resources

scripts/collect_release_changes.sh: Collect commits and touched files since last tag.
references/release-notes-guidelines.md: Language, filtering, and QA rules for App Store notes.