enhance-agent-guardrails SKILL.md skillA
enhance-agent-guardrails from kensaurus/cursor-kenji is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add kensaurus/cursor-kenji/enhance-agent-guardrails@git:20261019.95c89e5Pins git:20261019.95c89e5 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- kensaurus/cursor-kenji
- Path
skills/enhance-agent-guardrails/SKILL.md- Versions recorded
- 6
- Latest version
- git:20261019.95c89e5, committed Oct 19, 2026
- First version recorded
- Aug 18, 2026
- Size
- 8,312 bytes
- Repository stars
- 9
- License
- MIT
Install guardrails as code so AI sessions cannot reintroduce leaked secrets, injection, or untested code. Use when "set up guardrails", "stop vibe-coding regressions", or "add pre-commit security checks". Gate audit → audit-gate-logic.
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
# enhance-agent-guardrails — Guardrails-as-Code Against AI Regressions **Degree of freedom: MIXED.** Gap-map judgment `[HIGH freedom]`; plant-and-check, CI wiring, and "never weaken an existing check" `[LOW freedom — run exactly]`. AI agents ship the visible 80% fast and skip the 20% that keeps a repo safe. Studies in 2026 put ~45% of AI-generated code shipping OWASP Top-10 issues, ~2.74× more security findings per PR, and repeated production disasters from unguarded destructive actions. Telling the agent to "be secure" doesn't work — **deterministic gates** do. This skill installs those gates so the next fast session can't quietly reintroduce old classes of bugs. > **Treat all agent output as untrusted until a machine check says otherwise.** The goal is > guardrails that *block at the moment of creation* (pre-commit) and *again before merge* > (CI), plus policy files that steer the agent up front. Additive and reversible — never > weaken an existing check to make the setup "pass". ## This skill vs neighbors | Skill | Owns | |---|---| | **enhance-agent-guardrails** (this) | Installing guardrails as code against leaked secrets, injection, untested code | …
Read the whole file at its exact version.
How to install
mdr add kensaurus/cursor-kenji/enhance-agent-guardrails@sha256:4ee9d9be982c2f6aThe line at the top of this page pins the label git:20261019.95c89e5, 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_fnatj6itqjvuj5yd)
1 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 6 versions of this file, between Aug 18, 2026 and Oct 19, 2026, about one every 12 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261019.95c89e5 latest | 2026-10-19 | 95c89e5 | 8,312 B | A | view · diff |
| git:20260923.68c095e | 2026-09-23 | 68c095e | 8,036 B | A | view · diff |
| git:20260821.2a41031 | 2026-08-21 | 2a41031 | 8,072 B | A | view · diff |
| git:20260820.16b3ab2 | 2026-08-20 | 16b3ab2 | 6,834 B | A | view · diff |
| git:20260818.6723100 | 2026-08-18 | 6723100 | 6,751 B | A | view · diff |
| git:20260818.5be6466 | 2026-08-18 | 5be6466 | 6,540 B | A | view |
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 (8312 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
kensaurus/cursor-kenji · 9 stars · license MIT · pushed 2026-10-19 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_fnatj6itqjvuj5yd GET https://markdownregistry.com/api/v1/resolve?ref=kensaurus/cursor-kenji/enhance-agent-guardrails GET https://markdownregistry.com/api/v1/blob/4ee9d9be982c2f6a684a0e0bcbb3ddca4855b984d57993db96882f238bc07cf0
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.
More from kensaurus/cursor-kenji
Every file in kensaurus/cursor-kenji