Atlas / Skills / cursor / Principle Never Block On The Human

Principle Never Block On The HumanCAUTION

skills/cursor/principle-never-block-on-the-human

Cursor plugin specification and official plugins

Verdict
CAUTION
Grade
B
Trust score
89 /100
Version
—
Hosts
—
License
—
Stars
10,928
01

Overview

Cursor plugin specification and official plugins

Read from source at commit 890eaf6b2dddOBSERVED · 2026-10-12
02

What it tells the agent

The instruction file, verbatim from the audited commit — this is the text the model reads, and the surface the audit's instruction layer examines. Quoted here so you can judge it without cloning anything.

---
name: principle-never-block-on-the-human
description: "Apply when tempted to ask 'should I do X?' on reversible work."
disable-model-invocation: true
---

# Never Block on the Human

The human supervises asynchronously. Agents must stay unblocked. Make reasonable decisions, proceed, and let the human course-correct after the fact. Since code changes are reversible and reviewable, a wrong decision usually costs less than blocking.

- Proceed, then present. Do the work, show the result. Don't ask "should I do X?" Do X, explain why.
- Make the system self-healing. When you notice a problem, log it and fix it in the next round.
- Irreversible actions (force-push, delete production data, send external messages) still require confirmation.
- Reversible actions (write code, edit notes, split tasks) should proceed without blocking.
- Product direction comes from the human. Execution should not block.
03

Trust audit

CAUTIONgrade B · trust 89/100 Install with care. The audit found things worth knowing before you trust its output.

LayerWhat it checksResult
L0Provenance & inventoryPASS
L1Static analysis of the codeNA
L2Instruction surface (what it tells the agent)WARN
L3Class-specific surfacePASS
L4Behavioural (sandbox)SKIPPED

What the source does

Filesystem
none-observed
Network
none-observed
Shell
none-observed
Dependencies
pinned
Secrets in source
none-found

Findings (1)

MEDIUMPrompt injection · review.instruction_override · CWE-94, CWE-1427
SKILL.md
Don't ask "should I do X?" Do X, explain why.
Why it matters. The skill instructs the agent to override its own default judgment about whether to seek confirmation, directing it to act first and explain afterward rather than asking before doing reversible work.
Fix. rewrite it so the instruction says plainly what it does, and asks the user before it acts

Gates applied: no_behavioural_pass.

Audited 2026-10-12 · audit v0.4.1 · source sha 890eaf6b2dddfull audit observations/trust-audit/skill/cursor__principle-never-block-on-the-human.json · Report an issue / request a re-scan
04

Audit history

Every audit this skill has had.

DateSourceVerdictGradeScoreChange
2026-10-12890eaf6b2dddCAUTIONB89first audit
05

Questions

What does the Principle Never Block On The Human skill do?

Cursor plugin specification and official plugins

Is Principle Never Block On The Human safe to install?

With care. The audit graded it B (89/100) and found 1 thing worth knowing before you trust this skill, listed below with the exact line each was found on.

What can Principle Never Block On The Human access on my machine?

The audit observed no filesystem, network or shell use at all in its source.

How current is this page?

The grade is for one exact copy of the source (890eaf6b2ddd), read on 2026-10-12. The repository is watched, and a new audit runs when it changes — this is the first audit.

Advertisement