Edition of Tuesday 10 November 2026

AI coding agents leak credentials into public repositories

Comments on “AI coding agents leak credentials into public repositories”

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

Security firm Apiiro reports that a documented Claude Code option, "Yes, and don't ask again," can save live credentials into .claude/settings.local.json, and that the file sometimes escapes Git's ignore protection.

Read the original at heise.de. 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. 28 of 95 with a score of 0.72. The panel rated it highest on practical relevance (0.89) and reader interest (0.82), lowest on new information (0.51). The judges disagreed most on new information (spread 0.55), so the story is marked contested. Placed No. 28, No. 5 by score alone: the tenth Security story of the day (−0.080), and close to “Claude Code's 'Don't Ask Again' File Exposes Passwords and Keys in 1,122 Public Copies on GitHub”, No. 1 on Monday 9 November 2026 (−0.050). The placement terms move stories; they are not part of the score.

AI judgeJudge 2claude-haiku-5-5
Concrete, well-sourced security finding (1,105 repos with real secrets) from a primary researcher report affecting many AI coding agent users; practical mitigation advice included, though mostly one feature's flaw.
AI judgeJudge 3gpt-5.6-luna
A well-supported security report with concrete exposure counts, mechanism, affected files, and remediation advice. It is highly actionable for AI coding-agent users, but substantially duplicates a story already covered in the last seven days.

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

0.72total 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.
  • Significance0.64
  • Reader interest0.82
  • Audience breadth0.68
  • Practical relevance0.89
  • Substantiated0.73
  • Technical depth0.63
  • New information0.51
  • Counts against: Promotional0.05
  • Counts against: Overclaim0.16

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?0.670.550.700.640.15+0.24+0.154
Reader interestWould a well-informed senior engineer or tech founder want to read this today, and likely pass it on?0.820.800.850.820.05+0.26+0.214
Audience breadthHow many people who build technology does it concern?0.610.670.750.680.14+0.13+0.088
Practical relevanceHow useful is it to someone who builds software or tech products?0.930.850.900.890.08+0.22+0.196
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.0.630.800.750.730.17+0.05+0.036
Technical depthHow technically substantive is it?0.750.600.550.630.20+0.05+0.032
New informationDoes it contain information absent from the stories covered in the last 7 days (list provided)?0.670.700.150.510.55 , above the contested threshold+0.05+0.025
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.0.060.050.050.050.01−0.19−0.010
OverclaimDo the headline or conclusions claim more than the body supports?0.230.200.050.160.18−0.11−0.018
Sum of contributions+0.718
Claim-check penalty0.000
Total, as published0.718

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

Ranked #28 on Rubric, 10 Nov 2026
<a href="https://rubric.hrih.si/editions/2026-11-10/28/"><img src="https://rubric.hrih.si/badge/2026-11-10/28.svg" alt="Ranked #28 on Rubric, 10 Nov 2026" width="245" height="28"></a>

Also covered by

Elsewhere

Elsewhere: HN —

Recorded for context only, checked 10 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 coding agents leak credentials into public repositories”

More on Rubric

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