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 wgpsec/AboutSecurity --skill ai-infrastructure-attackgit clone --depth 1 https://github.com/wgpsec/AboutSecurityWrote 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/wgpsec/aboutsecurity/ai-infrastructure-attack)<a href="https://agentmods.dev/skills/wgpsec/aboutsecurity/ai-infrastructure-attack"><img src="https://agentmods.dev/badge/skills/wgpsec/aboutsecurity/ai-infrastructure-attack.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 | $0.00173 | $0.02656 |
| Opus 5 | $0.00086 | $0.01328 |
| Sonnet 5 | $0.00035 | $0.00531 |
| Haiku 4.5 | $0.00017 | $0.00266 |
Grade D, and why
ai-infrastructure-attack scanned grade D with 4 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 4d 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.
Sends data to an external URLmediumData exfiltration
A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.
curl -s http://TARGET:5000/api/2.0/mlflow/runs/search -X POST -d '{}' Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
curl -s http://TARGET:8265/api/jobs/ | python3 -m json.tool Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s http://TARGET:8888/api Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
-d '{"type":"notebook","content":{"cells":[{"cell_type":"code","source":"import os; os.system(\"id\")","metadata":{}}],"metadata":{"kernelspec":{"name":"python3"}},"nbformat":4}}' The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 4d ago First seen · 264 lines · 173 tokens per session scan D 8d7d07da959c
ai-infrastructure-attack is a skill published in the GitHub repository wgpsec/AboutSecurity (1,721 stars, last pushed 8d ago), with no licence file. It adds 173 tokens to every session and 2,656 once invoked, about $0.0009 per session on Opus 5. A static security scan graded it D with 4 findings (sends data to an external url, downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
ctf-ai-ml
Provides AI and machine learning techniques for CTF challenges. Use when attacking ML models, crafting adversarial examples, performing model extraction, prompt injection, membership inference, training data poisoning, fine-tuning manipulation, neural network analysis, LoRA adapter exploitation, LLM jailbreaking, or…
re-ai-model
A guide for examining machine-learning model files such as ONNX, PyTorch, Safetensors, and TFLite. It reconstructs network structure, extracts weights, and checks files for embedded markers or suspicious content.
re-ai-attack
A security-assessment guide for testing AI models through their visible interfaces or available model files. It covers model copying, behavioral fingerprints, training-data membership checks, privacy leakage, and resistance to adversarial examples, which are inputs designed to cause incorrect model behavior.
re-ai-triage
An entry point for analyzing the security and structure of artificial-intelligence models. It decides whether the input is a model file, an API, both, or a potentially malicious package, then sends the work to the relevant analysis path.
fieldops-prompt-decorators
Interprets and executes Prompt Decorators written with +++Name(key=value) syntax, handling message vs. chat scope, parameter validation, decorator composition, conflict resolution, meta-decorator expansion (N2 and Storm), retained-state inspection (ActiveDecs and AvailableDecs), selective clearing, and conversation…
dit
Classify HTML pages, forms, and fields using machine learning. Use when the user needs to detect page types (login, error, captcha), identify form types (login, search, registration), or classify form fields (username, password, email) from HTML content or URLs.