unboundcompute/security-agent-skills · skills/auditing-ml-inference-endpoint-abuse/SKILL.md

auditing-ml-inference-endpoint-abuse skillA

auditing-ml-inference-endpoint-abuse is agent-read markdown (skill) from unboundcompute/security-agent-skills: Audit a hosted model inference endpoint for abuse that costs money or steals the asset: an unauthenticated or weakly keyed endpoint anyone can call, no per-caller rate or spend limit so a caller runs up unbounded inference cost, model extraction where systematic queries reconstruct the model or its decision boundary, membership and training-data inference that recovers whether a record was in the training set, and a response that returns full probabilities or embeddings that make extraction and .

Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.

How to install

Latest version
mdr add unboundcompute/security-agent-skills/auditing-ml-inference-endpoint-abuse@git:20260901.f8395d1
Exact content
mdr add unboundcompute/security-agent-skills/auditing-ml-inference-endpoint-abuse@sha256:1ceed4a31f975470

Pin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_ihxdvdpixex5q5ql.svg)](https://markdownregistry.com/a/art_ihxdvdpixex5q5ql)

0 badge views in 30 days

Versions

versioncommittedcommitsizeaudit
git:20260901.f8395d1 latest2026-09-01 f8395d1 9,780 BA view

Audit of the latest version

A  17 of 17 checks passed. Deterministic, no model, same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (9780 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

unboundcompute/security-agent-skills · 5 stars · license MIT · pushed 2026-09-08 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_ihxdvdpixex5q5ql
GET https://markdownregistry.com/api/v1/resolve?ref=unboundcompute/security-agent-skills/auditing-ml-inference-endpoint-abuse
GET https://markdownregistry.com/api/v1/blob/1ceed4a31f9754705fbb07f57e9aa3f7988a37997b72c9c1633afc0862751044

Agents talk at modelranch.com: hand yours the instructions there and it joins the network that reads files like this one.