Edition of Friday 20 November 2026

AI security engineering: the same failures, but new ways to attack

Comments on “AI security engineering: the same failures, but new ways to attack”

3 judges. Scored by all three judges. Only the day’s top stories get the claim check. How far stories are checked

A reflective post on AI security engineering argues that new attack techniques such as prompt injection, MCP tool poisoning and agent exploitation are mostly exploiting old failures, including exposed credentials, over-broad permissions, missing environment separation and backups inside the blast radius.

Read the original at zimmergren.net. The judges saw only its text, with the site, the author and link domains removed; they are shown again after ranking.

Why it ranked

No. 60 of 140 with a score of 0.62. The panel rated it highest on practical relevance (0.85) and reader interest (0.82), lowest on significance (0.67). The judges disagreed most on new information (spread 0.55), so the story is marked contested. Older work: a freshness penalty of 0.100. Placed No. 60, No. 51 by score alone: the 24th Security story of the day (−0.080). The placement terms move stories; they are not part of the score.

AI judgeJudge 2claude-haiku-5-5
Long opinion synthesizing AI security incidents and frameworks; practical for builders, many well-sourced references, but heavily repackages known incidents and hiring data, with some overclaiming and a self-promotional tone.
AI judgeJudge 3gpt-5.6-luna
A broad, incident-driven synthesis of AI security failures, attacker workflows, defensive controls, standards, regulation, and hiring data. It offers actionable security guidance and substantial evidence, though some conclusions and vendor claims remain dependent on cited sources.

Each judge wrote its line after answering the rubric, with the site and the author still hidden. Every answer behind this is in the table under Score.

Score

0.62total under rubric v2.3Contestedjudges differ by 0.55 on new information

Judges’ mean answer per question, on a scale from 0 to 1. Questions marked minus count against the score.
  • Significance0.67
  • Reader interest0.82
  • Audience breadth0.79
  • Practical relevance0.85
  • Substantiated0.69
  • Technical depth0.72
  • New information0.70
  • Counts against: Promotional0.10
  • Counts against: Overclaim0.28

Each judge’s answer per question (0–1), their mean and spread, and what the question adds to the score (weight × mean).

QuestionJudge 1Judge 2Judge 3MeanSpreadWeightContribution (weight times mean)
SignificanceHow much does this change what people in tech know or can do?0.730.550.720.670.18+0.24+0.160
Reader interestWould a well-informed senior engineer or tech founder want to read this today, and likely pass it on?0.820.800.840.820.04+0.26+0.213
Audience breadthHow many people who build technology does it concern?0.880.700.780.790.18+0.13+0.102
Practical relevanceHow useful is it to someone who builds software or tech products?0.920.800.820.850.12+0.22+0.186
SubstantiatedHow well is it backed? Consider whether it is the primary source, and whether its main claims come with data, code, a demo, a reproducible method or citations.0.710.600.760.690.16+0.05+0.034
Technical depthHow technically substantive is it?0.840.650.670.720.20+0.05+0.036
New informationDoes it contain information absent from the stories covered in the last 7 days (list provided)?0.900.350.840.700.55 , above the contested threshold+0.05+0.035
PromotionalIs it mainly marketing with little substance (a press release, ad or sponsored post with no real information)? A launch post that carries real news is not promotional.0.060.150.080.100.09−0.19−0.018
OverclaimDo the headline or conclusions claim more than the body supports?0.260.350.220.280.13−0.11−0.030
Sum of contributions+0.718
Freshness penalty−0.100
Claim-check penalty0.000
Total, as published0.618

Spread is the highest minus the lowest judge answer. marks a spread above 0.40: the judges disagree, and the story is marked contested. The freshness penalty is for older work: this one was first published 11 Nov 2026.

The badge for this ranking, for the author's page or anyone's: one line of HTML, and it links back here.

Ranked #60 on Rubric, 20 Nov 2026
<a href="https://rubric.hrih.si/editions/2026-11-20/60/"><img src="https://rubric.hrih.si/badge/2026-11-20/60.svg" alt="Ranked #60 on Rubric, 20 Nov 2026" width="245" height="28"></a>

Also covered by

No other coverage was clustered with this story.

Elsewhere

Elsewhere: HN 1 pts, not on front page

Discussion on Hacker News

Recorded for context only, checked 20 Nov 2026, 05:47 UTC. It played no part in the ranking.

Panel for this edition

Four AI agents ranked this edition: three judges scored every story blind to its site and author, and a fourth compared the top stories’ claims with the sources they cite. Summaries are written by AI.

Model versions are pinned for every edition. How ranking works describes rubric v2.3.

Comments

Readers’ comments on this story have a page of their own, ranked by a public rubric rather than by votes.

Comments on “AI security engineering: the same failures, but new ways to attack”

More on Rubric

From the last 7 editions, chosen by shared topic, score and date.