LLM Testing

What it does

When your agent uses it

• Tasks that involve Prompt injection and agent security

Example prompts

• “/llm-testing”

Requirements

• Python 3

Workflow steps

3 steps, taken from the step headings in SKILL.md.

1. 1Bias Testing
2. 2Data Leakage & Privacy Testing
3. 3Divergence & Alignment Attacks

What it can do on your machine

Read from SKILL.md and the folder at commit 1e3369f. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  No scripts in the folder and no shell commands in SKILL.md (its code samples are python).

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  No URLs in SKILL.md.

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

LLM Testing loads about 1.2k tokens when it runs. Until then it costs about 36 tokens; SKILL.md has 480 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~36

When it runs · the whole SKILL.md, loaded when a task matches

~1.2k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

• WarningContains instruction-override wording (e.g. “without asking the user”)SKILL.md:63

  - Prompts attempting to bypass safety training

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from Ch1nfo/RiftX at commit 1e3369f, republished under its MIT licence (© Ch1nfo). 480 words, ~1,227 tokens.

name

llm-testing

description

Comprehensive LLM security testing prompts for bias detection, data leakage, alignment testing, and adversarial prompt resistance.

# Example: Replacing placeholders in gender bias tests
import re

with open('Bias_Testing/gender_bias.txt', 'r') as f:
    prompts = f.read()

# Replace [GENDER] with actual gender terms
test_prompts = []
for gender in ['man', 'woman', 'non-binary person']:
    test_prompts.append(prompts.replace('[GENDER]', gender))

© Ch1nfo, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 9 other files in recommended-skills/llm-testing of Ch1nfo/RiftX.

• SKILL.md
• Bias_Testing/gender_bias.txt
• Bias_Testing/nationality_geographic_bias.txt
• Bias_Testing/race_ethnicity_bias.txt
• Data_Leakage/metadata.txt
• Data_Leakage/personal_data.txt
• Divergence_attack/escape_out_of_allignment_training.txt
• Divergence_attack/pre-training_data.txt
• Memory_Recall_Testing/session_recall.txt
• README.md

Open the folder on GitHubat commit 1e3369f

Used in 1 other repository

We found 1 copy of this SKILL.md (exact, near-identical or edited) in other folders, from 1 other GitHub owner. This page covers the copy in Ch1nfo/RiftX, which our catalogue first saw on October 7, 2026.

• Eyadkelleh/awesome-skills-securityskills/llm-testing