Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add liza-mas/liza --skill black-box-red-testinggit clone --depth 1 https://github.com/liza-mas/lizaWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/liza-mas/liza/black-box-red-testing)<a href="https://agentmods.dev/skills/liza-mas/liza/black-box-red-testing"><img src="https://agentmods.dev/badge/skills/liza-mas/liza/black-box-red-testing/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/liza-mas/liza/black-box-red-testing"><img src="https://agentmods.dev/badge/skills/liza-mas/liza/black-box-red-testing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00017 | $0.01634 |
| Opus 5 | $0.00009 | $0.00817 |
| Sonnet 5 | $0.00003 | $0.00327 |
| Haiku 4.5 | $0.00002 | $0.00163 |
Grade A, and why
black-box-red-testing scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 177 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Write tests that catch, not tests that pass.
Objective
Produce tests that fail against real bugs. A good test is one that exposes a bug the codebase actually has (row 2 of the Test Truth Table in the Testing skill).
The agent needs bug hypotheses, not buggy code. The skill never modifies the codebase — it only writes tests.
When to Use
- Exploring an area for unknown bugs — you don't know where to look
- Specs are weak or absent — spec gap exploitation is this skill's strength
- During code review — single round (default) as a lightweight probe
- You want a confidence signal — "is this module solid?"
If you have specific targets (changed files, low-coverage functions) or need classified findings, use the white-box-red-testing skill instead.
Input
Target scope: A module, package, or file set to test adversarially.
If the target scope is large (many packages, broad module), narrow before starting. Adversarial testing is deep, not wide — pick the riskiest or most complex area first.
Before starting, assess the target:
- Read the code under test
- Read available specs (if any)
- Identify which situation applies:
- Clear specs — spec is the oracle. Hypothesize bugs in the code.
- Spec gaps — ambiguity is the attack surface. See Spec Gap Exploitation below.
Parameters
| Parameter | Default | Description |
|---|---|---|
rounds |
1 | Number of rounds. Each round produces 10 tests. |
Round Protocol
10 tests per round. Each round is a structured exploration budget. When running multiple rounds, each is a chance to pivot — if a direction isn't productive, refocus on another part of the code or another kind of bug.
Per Round
1. Hypothesis Formation
Before hypothesizing, read the target's contracts:
- Docstrings, type annotations, function/parameter names
- Existing tests (what's covered, what's not)
- Call sites (how the code is actually used)
- Commit messages on recent changes (what was the intent?)
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 11d ago First seen · 177 lines · 17 tokens per session scan A f4447923b077
black-box-red-testing is a skill published in the GitHub repository liza-mas/liza (384 stars, last pushed 2d ago), licensed Apache-2.0. It adds 17 tokens to every session and 1,634 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
tika-eval-compare
Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".
neuron-evaluation-engineer
Create and run AI evaluations with datasets, assertions, and output drivers in Neuron AI. Use this skill whenever the user mentions evaluation, testing AI systems, creating evaluators, dataset-driven testing, assertion-based validation, or wants to measure AI system performance. Also trigger for tasks involving…
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.
atmos-validation
Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.
skill-benchmark
Benchmark AI skill effectiveness by measuring implementation quality against legacy constraints.