Skip to content
NewA calmer, faster ZeroHour

Essay casts prompt injection as social engineering of models

Original title: AI Security Issues Are Social Engineering Issues

Lobsters · securityby oblomovka.com by dannyob ()5 min read1
AI summary · x-ai/grok-4.7Summaries by Vani AI

The author argues capability-based security, as in CHERI and Cloudflare Workers, limits confused-deputy abuse of model instructions.

An essay compares prompt injection to social engineering, arguing that models follow instructions hidden in content the way people can be tricked. It says capability-based security gives a program only the authority needed for a task, limiting confused-deputy abuse. The author points to existing work including CHERI, Fuchsia, Capsicum, Cap’n Proto, Cloudflare Workers, and Spritely’s OCapN, and hopes AI-assisted reengineering will help adoption.

Unconfirmed: The essay’s “Black October” flaw wave is the author’s framing, not a documented incident in the text.

Key facts
  • The essay says smuggled instructions can range from style changes to requests for known data.
  • It names Unix file descriptors and WASI as existing capability bubbles.
  • CHERI encodes capabilities in hardware; Capsicum ports the model to existing software.
  • Spritely, funded via the Filecoin Foundation, built object capabilities and OCapN.
Explain this AI news with Vani AIWhat was announced, what is new and why it matters, in a new chat

From the original article

5 min read at oblomovka.com

When I was at EFF in the 2010s, I spent a lot of time fretting about the fundamental security of networked devices. Apart from the usual concerns, I struggled to imagine a transition to a redecentralized future with fragile personal computers and servers. Peter Eckersley , my co-worker and frequent conversation partner, shared my concern, but had another reason to be worried.

Lobsters · security

By oblomovka.com by dannyob · oblomovka.com

Read the full article at Lobsters · security

A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.