One prompt makes a fake receipt: fileForensics runs 55 checks before agents trust files
thisiskp_ · x · 2026-11-04
KP highlights a new risk: a fake receipt now takes one prompt to make, and most apps and agents will read, extract and act on it without verifying it. He's launching fileForensics (by fileAI) on Product Hunt to check files before your app or agent trusts them.
How it works:
- Upload a file or call the API
- 55 checks in one pass: file structure, edit history, pixels, AI-generated content, inconsistent details
- Each finding comes with evidence — what, where, why — not a black-box score
In Claude, Cursor or Codex, add the MCP server and ask "can I trust this invoice?"
More from coding & agent
- Weaviate ships Boost soft re-ranking in v1.38, with an 81k-product search recipe — CShorten30 · 2026-11-04
- AI can write more code, but engineers still must engineer the system — rseroter · 2026-11-04
- Microsoft Clarity adds Agentic Analytics as AI agent traffic nearly doubles to ~2M in 3 weeks — OnlineInference · 2026-11-04
- Agentic Engineering vs AI Engineering: how the two disciplines actually differ — Pavan_Belagatti · 2026-11-04
- Grok Bot Books a Flight End-to-End: Search, Payment, and Bank Verification in One Chat — XFreeze · 2026-11-04
- OpenAI acquires Pierre to make Codex a collaborative AI software-building platform — OpenAINewsroom · 2026-11-04