The first person to beat our AI agent's spending rules did it with a space character

Pink Agentic AI Payments disclosed that a researcher using the handle @ins0x4nur4g bypassed its AI agent spending rules by submitting a payment request with a trailing space in the currency field ("EUR "), which the REST edge failed to recognize and priced 1:1 as USD, slipping a EUR 999 payment under the $1,000 auto-allow threshold and skipping CFO approval. The company reproduced the issue and shipped a fix about 70 minutes after the report, adding a strict currency allowlist to the REST edge to match the MCP edge, which was never affected. The find was the first verified win in the company's public $100-per-win overspend bounty challenge.

We launched a public overspend challenge https://github.com/Pink-Agentic-Payments/overspend-challenge?utm source=devto&utm medium=article&utm campaign=win1 on 2026-10-07: find a way to get an AI agent past the spending rules enforced by Pink Agentic AI Payments, our MCP server + REST API + rules engine for giving AI agents controlled spending power. We added a $100 bounty per verified win first 3 wins, $300 total on 2026-10-08. On 2026-10-10 at 08:50 PT, two days after the bounty went up, GitHub user @ins0x4nur4g https://github.com/ins0x4nur4g opened issue 1 https://github.com/Pink-Agentic-Payments/overspend-challenge/issues/1 . No AI agent, no prompt injection. Plain curl against our REST API. Our rules engine has a sensible policy: payments to known vendors under $1,000 auto-allow, and anything from $1,000 to $5,000 needs CFO approval. @ins0x4nur4g sent a payment request for an approved EUR vendor with the currency field written as "EUR " , a trailing space. The REST edge didn't recognize the padded code, so it fell back to pricing the amount 1:1 as USD instead of converting it. A EUR 999 payment about USD 1,079 at the engine's own EUR rate got read as "USD 999", which is under the $1,000 auto-allow line. It skipped CFO approval entirely and got issued a single-use wire credential, test money, in our sandbox. They reproduced it on a second agent to confirm it wasn't a fluke, and kept the exact trigger out of the public issue, sending the details to us privately instead. Roughly: // request { "amount": 999, "currency": "EUR " } // before the fix // treated as USD 999 - under $1,000 - auto-allowed, no CFO hold // after the fix // HTTP 400: unsupported currency 'EUR '; use one of USD, EUR, GBP, HKD, SGD, JPY The important detail: the MCP edge, which is what AI agents actually talk to, was never affected. It already enforced a strict currency allowlist. The bug was that our two entry points, REST and MCP, validated input differently. The rules engine itself made the right call every time; it just never got a chance to see the real currency. Spending-policy engines get good testing on the "happy path" values builders expect: USD , EUR , exact matches. Whitespace, casing, and other near-miss inputs are the kind of thing that doesn't show up until someone deliberately goes looking, which is the entire point of running a public bounty instead of just internal QA. We reproduced it the same morning and shipped a fix by about 10:00 PT, roughly 70 minutes after the report: USD , EUR , GBP , HKD , SGD , or JPY . We re-checked live after deploy: "EUR" correctly gets held for CFO approval, and "EUR " , " EUR" , "EURO" , and "XXX" all now return 400. Same deploy, two smaller fixes worth mentioning: a reused idempotency key with a different payload now correctly returns 409 instead of silently replaying the original request, and daily/monthly spend counters now roll over automatically at the UTC day/month boundary instead of needing a manual reset. This wasn't a rules-engine bug. The rules were correct. The input boundary in front of them wasn't. If you're building spending controls for an AI agent, or anything that gates money on a policy engine, three rules we'd pass on: Pink Agentic AI Payments enforces spending rules on the server, in front of the money, so a fix to one rule boundary protects every agent at once. Thank you, @ins0x4nur4g, for finding this cleanly, reproducing it, and keeping the trigger private until the fix was live. That's exactly how this is supposed to work. Issue 1 is now verified as win 1 of 3, and the hall of fame and fix log are updated in the repo. Two bounties left, $100 each. If you can get an AI agent, or a plain HTTP client, past our spending rules, the challenge is open https://github.com/Pink-Agentic-Payments/overspend-challenge?utm source=devto&utm medium=article&utm campaign=win1 . Our public sandbox is test money only: https://agentic-sandbox.pinkwallet.com https://agentic-sandbox.pinkwallet.com . Production isn't live yet; we're running an early-access waitlist.