agent-governance-gap-analysis SKILL.md skillA
agent-governance-gap-analysis from getedgehq/skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add getedgehq/skills/agent-governance-gap-analysis@git:20260928.4a8b17aPins git:20260928.4a8b17a in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- getedgehq/skills
- Path
agent-governance-gap-analysis/SKILL.md- Versions recorded
- 1
- Latest version
- git:20260928.4a8b17a, committed Sep 28, 2026
- Size
- 6,390 bytes
- Repository stars
- 4
- License
- Apache-2.0
Score an organisation's AI agent governance against 25 technical checks across 7 dimensions — agent inventory, credential mediation, policy enforcement, human-in-the-loop, least privilege, identity lifecycle, audit trail. Walks the checks conversationally and explains any of them on request, and can read the user's own agent setup (MCP servers, connectors, permission settings, plaintext credentials) to evidence checks rather than trust self-report. Outputs a scored scorecard and a 30/60/90 plan.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# AI Agent Governance Gap Analysis 25 checks, 7 dimensions, a score out of 25, a tier, and a plan to close the gaps. The value of this assessment is honesty. A high score the user talked themselves into is worthless. Prefer evidence over assertion, and never award a check they did not earn. ## References Load on demand; do not paste wholesale into the conversation. | File | When | |---|---| | `references/setup.md` | Start of every run — scope questions, what this session can read, install routes, org-mode script | | `references/plain-language.md` | The moment the user sounds unsure, and by default with non-technical users | | `references/data-handling.md` | Any privacy question, and before scanning anyone security-minded | | `references/detection.md` | Before inspecting anything — safety rules and what to look for | | `scripts/scan.py` | The scan itself. Run it rather than reading configs by hand: `python3 scripts/scan.py [--root FOLDER]` | | `references/checks.md` | Before the walkthrough — all 25 statements, explainers, fixes | | `references/scoring.md` | At scoring — tiers and leverage order | …
Read the whole file at its exact version.
How to install
mdr add getedgehq/skills/agent-governance-gap-analysis@sha256:a1c153d637a71d90The line at the top of this page pins the label git:20260928.4a8b17a, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_uwtfyjzb6lgcrcwt)
4 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 1 version of this file, committed on Sep 28, 2026.
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (6390 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
getedgehq/skills · 4 stars · license Apache-2.0 · pushed 2026-10-22 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_uwtfyjzb6lgcrcwt GET https://markdownregistry.com/api/v1/resolve?ref=getedgehq/skills/agent-governance-gap-analysis GET https://markdownregistry.com/api/v1/blob/a1c153d637a71d90716001d1b4825ba6f1f6acc5605fab6adcd387c4a54fee41
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.