unboundcompute/security-agent-skills · skills/auditing-idp-initiated-flow-trust/SKILL.md

auditing-idp-initiated-flow-trust skillA

auditing-idp-initiated-flow-trust is agent-read markdown (skill) from unboundcompute/security-agent-skills: Audit identity-provider-initiated single sign-on for trust placed in an unsolicited assertion the application never asked for: an IdP-initiated SAML response the service provider accepts with no matching request so there is no request state to bind it to, an unsolicited assertion an attacker captures and replays or delivers to a victim to log them into an attacker-chosen account, a RelayState value trusted as a redirect target so it becomes an open redirect, an assertion with no or a too-wide au.

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-idp-initiated-flow-trust@git:20260903.19a7174
Exact content
mdr add unboundcompute/security-agent-skills/auditing-idp-initiated-flow-trust@sha256:2841c3a88bbd59dc

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_l3vemzvcn5pqxsp4.svg)](https://markdownregistry.com/a/art_l3vemzvcn5pqxsp4)

0 badge views in 30 days

Versions

versioncommittedcommitsizeaudit
git:20260903.19a7174 latest2026-09-03 19a7174 10,982 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 (10982 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_l3vemzvcn5pqxsp4
GET https://markdownregistry.com/api/v1/resolve?ref=unboundcompute/security-agent-skills/auditing-idp-initiated-flow-trust
GET https://markdownregistry.com/api/v1/blob/2841c3a88bbd59dceb6c97e129da42de1cc6500c61138df40e31120187b907f9

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