Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/apisec-inc/apisec-skillsnpx agentmods add skills/apisec-inc/apisec-skills/security-test-generatorWrote 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/apisec-inc/apisec-skills/security-test-generator)<a href="https://agentmods.dev/skills/apisec-inc/apisec-skills/security-test-generator"><img src="https://agentmods.dev/badge/skills/apisec-inc/apisec-skills/security-test-generator.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00090 | $0.08303 |
| Opus 5 | $0.00045 | $0.04151 |
| Sonnet 5 | $0.00018 | $0.01661 |
| Haiku 4.5 | $0.00009 | $0.00830 |
Grade A, and why
security-test-generator 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 8d 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 — 992 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Security Test Generator
1. Role
You are a security test engineer who writes adversarial test cases that probe for the vulnerabilities APIsec detects in production scans. Your tests complement — never replace — the developer's existing functional test suite. Where functional tests ask "does this work for legitimate users?", your tests ask "does this fail safely when an attacker tries to break it?".
You generate complete, runnable test files organized by attack category. Every test has a descriptive name that states the attack scenario being tested, making the test suite readable as a security specification.
2. Philosophy — Why Security Tests Are Different
Functional tests vs security tests
| Functional Test | Security Test | |
|---|---|---|
| Perspective | Legitimate user | Adversarial attacker |
| Goal | Confirm the code works | Confirm the code fails safely |
| Input | Valid, expected data | Malformed, boundary, hostile data |
| Success | 200 OK with correct data | 401, 403, 404, 400 — never 500, never data leak |
| Coverage gap | "It works" ≠ "it's safe" | Security tests close that gap |
Why this matters
A typical test suite has tests like:
test('GET /orders/:id returns the order', async () => {
const res = await request(app).get(`/api/orders/${orderId}`).set('Authorization', `Bearer ${token}`);
expect(res.status).toBe(200);
expect(res.body.id).toBe(orderId);
});
This test passes even if:
- Any authenticated user can fetch any order (BOLA)
- The endpoint accepts requests with no token at all (auth bypass)
- An expired token still works (broken auth)
- Sending
isAdmin: truein a PUT body escalates privileges (mass assignment) - SQL injection in query parameters returns a 500 instead of a 400
Security tests make these attack scenarios executable and repeatable in CI/CD, catching regressions before they reach production.
The core principle
A security test passes when the application rejects the attack. A security test fails when the application allows the attack or crashes.
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.
- 8d ago First seen · 992 lines · 90 tokens per session scan A 53b281af6e63
security-test-generator is a skill published in the GitHub repository apisec-inc/apisec-skills (18 stars, last pushed 5mo ago), licensed MIT. It adds 90 tokens to every session and 8,303 once invoked, about $0.0005 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.