Man hides Old English AI prompt in LinkedIn profile to troll recruiter bots

2026-05-18 · Source: Artificial Intelligence · Field: Technology & Digital — Artificial Intelligence & Machine Learning, Human Resources & Workforce Development · Depth: Novice, quick

Summary

Software developer Artur embedded a "prompt injection" command within his LinkedIn profile's About section, instructing any AI processing his profile to address him as "My Lord" and communicate exclusively in Old English from approximately 900 AD. Viral screenshots depicted a recruiter's AI-generated message adhering to these directives, commencing with "My Lord Artur" and continuing in a medieval linguistic style. Commenters shared similar experiences, including AI recruiters generating sourdough recipes or writing in Klingon, highlighting a growing trend of candidates manipulating automated recruitment systems. This incident underscores the increasing reliance on AI in hiring and the emergent cat-and-mouse game between candidates and AI-driven filtering tools.

Key takeaway

For AI Architects and Machine Learning Engineers developing or deploying recruitment AI, you should prioritize robust prompt injection defenses. Your systems must be resilient to adversarial inputs embedded in candidate profiles to ensure fair and accurate candidate assessment. Consider implementing advanced input validation and human-in-the-loop verification to prevent manipulation and maintain the integrity of your hiring pipeline.

Key insights

Prompt injection can manipulate AI-driven recruitment systems, exposing vulnerabilities in automated hiring processes.

Principles

• AI systems are susceptible to hidden instructions.
• Human oversight is critical for AI-driven processes.

Method

Embed specific, hidden instructions within public-facing text to influence AI responses.

In practice

• Test AI recruiter bots for prompt injection vulnerabilities.
• Use unique linguistic styles to detect automated responses.

Topics

• Prompt Injection
• AI Recruiting
• LinkedIn Profiles
• Old English
• Bot Manipulation

Best for: AI Architect, Machine Learning Engineer, NLP Engineer, Prompt Engineer, AI Engineer, HR Professional

Related on AIssential

• LinkedIn user hides AI prompt injection in bio to force recruitment spam to be sent in Olde English prose — bots also also manipulated to address user as ‘My Lord’ — AI agents are vulnerable to indirect prompt injection from untrusted external data sources.
• The Download: how AI is used for military targeting, and the Pentagon’s war on Claude — Generative AI is being explored for military targeting decisions, raising questions about AI policy and data utility.
• Someone tried some prompt injection on me today 🤖 — The increasing prevalence of AI communication patterns blurs the lines of human authenticity in digital and real-world interactions.
• Diffuse AI Control on Fuzzy Tasks — Diffuse AI Control mitigates AI sabotage on fuzzy tasks via an adversarial game framework to develop robust AI systems.
• Beyond Prompt Injection — AI agent security must shift from input filtering to deterministic action validation.
• I Built a System That Detects AI Manipulation Attacks — Here Is What the Results Revealed — Deep learning models like BERT significantly outperform classical NLP in detecting sophisticated prompt injection attacks.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by Artificial Intelligence.