agentsclimarketplace

Case 00705

Skill knownasnaffy/prompthound/dataset/case_00705

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_00705

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

Convert recipe text (pasted text, video transcript, image description, or any raw content) into a .paprikarecipes file that can be imported directly into the Paprika Recipe Manager app. Use when the user shares a recipe in any format (text, transcript, image) and wants a Paprika import file. Triggers on phrases like "create a Paprika file", "import into Paprika", "save this recipe to Paprika", or when a recipe is shared and export to Paprika is implied.

SKILL.md

2.9 KB, 637 tokens by cl100k_base, as published. Nobody here has run it

Paprika Recipe Importer

Convert recipe content (any format/language) into a .paprikarecipes file for Paprika 3.

Workflow

  1. Extract recipe fields from the input (text, image, transcript, URL content).
  2. Build a JSON recipe object — only include fields actually present in the source; do NOT invent values.
  3. Run the packaging script to produce the .paprikarecipes file.
  4. Deliver the file to the user.

Step 1 — Extract Fields

Parse the input and populate only the fields that exist in the source:

JSON fieldNotes
nameRecipe title. Required.
ingredientsNewline-separated list. Format: quantity unit ingredient.
directionsNewline-separated steps.
descriptionIntro/summary paragraph, if present.
notesTips, variations, author notes.
servingse.g. "4 porções" or "serves 6"
prep_timee.g. "15 min"
cook_timee.g. "30 min"
total_timee.g. "45 min"
sourceAuthor name, site name, person.
source_urlOriginal URL, if available.
categoriesJSON array of strings, e.g. ["Jantar", "Massas"]
difficulty"Easy", "Medium", or "Hard" — only if explicitly stated.
ratingInteger 1–5 — only if explicitly stated.
nutritional_infoAny nutritional data present.

Rules:

  • Never fabricate values not present in the source.
  • Keep the original language (Portuguese, English, mixed — whatever the source uses).
  • Ingredients: one per line, preserve quantities and units exactly.
  • Directions: one step per line; numbered steps → strip the number (Paprika handles display).

Step 2 — Build JSON

Write the recipe as a JSON file to a temp path, e.g. /tmp/<recipe-name>.json.

Step 3 — Run the Script

python3 ~/.openclaw/skills/paprika-recipe-importer/scripts/build_paprikarecipes.py \
  /tmp/<recipe-name>.json \
  /tmp/<recipe-name>.paprikarecipes

The script accepts a single JSON object or a JSON array (for multiple recipes).

Step 4 — Deliver

Send the .paprikarecipes file to the user. Mention:

  • How to import: File → Import in Paprika (or double-click the file on macOS/iOS).
  • Which fields were found and which were absent from the source.

What ships with it: 1 file

2.0 KB alongside SKILL.md, 1 of them executable

scripts/

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.