unboundcompute/security-agent-skills · skills/auditing-browser-extension-trust/SKILL.md

auditing-browser-extension-trust skillA

auditing-browser-extension-trust is agent-read markdown (skill) from unboundcompute/security-agent-skills: Audit a browser extension (Manifest V3) for a trust boundary another web page or extension can cross to reach a privileged capability, after the permission scope and the message-sender checks are resolved. Covers an externally_connectable or onMessageExternal handler that verifies an origin but not the calling script, a content-script-to-background message handler with no sender validation, host permissions broader than the extension needs, a web_accessible_resources page that acts on URL parame.

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-browser-extension-trust@git:20260825.70f8609
Exact content
mdr add unboundcompute/security-agent-skills/auditing-browser-extension-trust@sha256:835978bed1b3124d

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_7tdjghhqn7okl3ni.svg)](https://markdownregistry.com/a/art_7tdjghhqn7okl3ni)

0 badge views in 30 days

Versions

versioncommittedcommitsizeaudit
git:20260825.70f8609 latest2026-08-25 70f8609 9,944 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 (9944 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_7tdjghhqn7okl3ni
GET https://markdownregistry.com/api/v1/resolve?ref=unboundcompute/security-agent-skills/auditing-browser-extension-trust
GET https://markdownregistry.com/api/v1/blob/835978bed1b3124d03a0804c6192829d342815bbfc6dcfacfd2e31e76dc96bc1

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