What is a prompt escape hatch?

A phrase or omission that gives the model permission, intentionally or not, to do something other than what you meant. Common examples are vague hedges like "try to," conditionals with no else-branch, and instructions that never define what counts as out of scope.

How does the detection work?

The tool scans for known weak-instruction patterns — hedge verbs, soft modal words ("should," "ideally"), open-ended conditionals, undefined pronouns, and missing fallback instructions — using heuristics. It does not call an LLM, so it is fast and private.

Will fixing every flag make my prompt better?

Usually, but use judgement. Some hedging is intentional. The tool surfaces candidates and explains the risk; you decide which to tighten based on how strict the task needs to be.

Is my prompt sent anywhere?

No. All analysis happens in your browser with JavaScript. Nothing is uploaded or stored, so you can safely audit proprietary system prompts.

What is the single highest-value fix?

Adding explicit fallback instructions — "if you cannot do X, respond with Y" — closes the most common escape hatch, where the model invents its own behavior because you never told it what to do when a condition fails.

Prompt Escape Hatch Detector

Prompt escape hatch detector

LLMs follow the letter of your instructions, not the spirit. Any vagueness becomes a loophole: a hedge word lets the model “mostly” comply, an open conditional with no else-branch lets it improvise, and an undefined scope lets it wander off-task. This tool scans your prompt for those escape hatches and explains how each one could be exploited so you can close it.

How it works

The detector runs a set of heuristics against your prompt text — no model call, no network. It flags hedge verbs (“try to,” “attempt to”), soft modals (“should,” “ideally,” “if possible”), conditionals that never specify the negative branch, vague quantifiers (“some,” “a few,” “appropriate”), undefined references, and the absence of any explicit fallback instruction. Each finding names the offending phrase, categorizes the weakness, and tells you why a model could use it to deviate.

Tips and notes

Replace soft modals with imperatives. “You should cite sources” becomes “Cite a source for every claim; if none exists, write ‘no source’.”
Always add a fallback. The most reliable prompts say exactly what to do when the main path fails.
Define out-of-scope explicitly. State what the model must refuse or redirect, rather than assuming it will infer the boundary.
Some hedging is fine. Creative or exploratory prompts may want looseness — the tool flags candidates, you make the call. Everything stays in your browser.