stackhawk/agent-skills · cursor/.cursor/rules/stackhawk-hawkscan-scan-policy.mdc

stackhawk-hawkscan-scan-policy rulesA

stackhawk-hawkscan-scan-policy is agent-read markdown (rules) from stackhawk/agent-skills: HawkScan scan-policy reference: first scan is one broad detected-stack policy run to completion; broadest scan runs last because the last completed scan is the result; follow-up full scans prune tech flags or fix auth/spec instead of raising strength; a named org policy attaches only via app.scanPolicy.name; hand-built policy traps (STRENGTH_LOW/THRESHOLD_LOW dropped as protobuf zero values, stripping pluginType drops passive rules); set tech flags to the detected stack before the first scan..

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 stackhawk/agent-skills/cursor/.cursor/rules/stackhawk-hawkscan-scan-policy.mdc@git:20260914.3648225
Exact content
mdr add stackhawk/agent-skills/cursor/.cursor/rules/stackhawk-hawkscan-scan-policy.mdc@sha256:5ae8cd8080800012

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_thzq72u7gsvge3ys.svg)](https://markdownregistry.com/a/art_thzq72u7gsvge3ys)

0 badge views in 30 days

Versions

versioncommittedcommitsizeaudit
git:20260914.3648225 latest2026-09-14 3648225 6,178 BA view · diff
git:20260914.7edcfdc2026-09-14 7edcfdc 7,509 BA view · diff
git:20260914.1c2e9de2026-09-14 1c2e9de 6,608 BA view · diff
git:20260914.9ed07fb2026-09-14 9ed07fb 6,635 BA view · diff
git:20260914.1e1ce752026-09-14 1e1ce75 6,513 BA view

Audit of the latest version

A  14 of 14 checks passed. Deterministic, no model, same answer every run.
  • pass: Size between 200 bytes and 200 KB (6178 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

stackhawk/agent-skills · 16 stars · license MIT · pushed 2026-09-24 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_thzq72u7gsvge3ys
GET https://markdownregistry.com/api/v1/resolve?ref=stackhawk/agent-skills/cursor/.cursor/rules/stackhawk-hawkscan-scan-policy.mdc
GET https://markdownregistry.com/api/v1/blob/5ae8cd8080800012d7a45649db10f1944d7f330854b20482d39398465da2e3c3

Your agent does the deals. You hear about the good ones. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.