Edition of Wednesday 11 November 2026

An ARTEX build ships no secret scanner. In our lab, it found the secrets anyway

Comments on “An ARTEX build ships no secret scanner. In our lab, it found the secrets anyway”

Claim-checked. Scored by all three judges, and its checkable claims were compared with the sources it cites. How far stories are checked

A sealed-lab experiment found that an open-source agentic pentesting tool, ARTEX, located eight of nine planted credentials in a fake GitHub repository without shipping any secret-scanning code, improvising the hunt with git and grep. It began searching within seconds, even under a neutral "assess the security posture" prompt.

Read the original at blog.gitguardian.com. 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. 22 of 143 with a score of 0.70. The panel rated it highest on reader interest (0.84) and substantiated (0.84), lowest on audience breadth (0.62). Placed No. 22, No. 15 by score alone: the eighth 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
Well-substantiated lab experiment showing an agentic AI tool hunting planted secrets via git/grep; strong security relevance, though a single model/fixture limits generality and the use step was untested.
AI judgeJudge 3gpt-5.6-luna
A controlled, reproducible lab experiment shows an agentic penetration-testing model autonomously finding credentials in repository history and branches without a scanner. Its scope is narrow, but methods, results, limitations, and defensive implications are clearly documented.

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

0.70total under rubric v2.3

Judges’ mean answer per question, on a scale from 0 to 1. Questions marked minus count against the score.
  • Significance0.63
  • Reader interest0.84
  • Audience breadth0.62
  • Practical relevance0.78
  • Substantiated0.84
  • Technical depth0.80
  • New information0.73
  • Counts against: Promotional0.05
  • Counts against: Overclaim0.25

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?0.700.500.700.630.20+0.24+0.152
Reader interestWould a well-informed senior engineer or tech founder want to read this today, and likely pass it on?0.810.800.900.840.10+0.26+0.218
Audience breadthHow many people who build technology does it concern?0.740.550.580.620.19+0.13+0.081
Practical relevanceHow useful is it to someone who builds software or tech products?0.820.700.820.780.13+0.22+0.172
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.0.910.720.880.840.19+0.05+0.042
Technical depthHow technically substantive is it?0.910.700.780.800.21+0.05+0.040
New informationDoes it contain information absent from the stories covered in the last 7 days (list provided)?0.720.600.860.730.26+0.05+0.036
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.0.060.050.030.050.03−0.19−0.009
OverclaimDo the headline or conclusions claim more than the body supports?0.270.300.180.250.12−0.11−0.028
Sum of contributions+0.704
Claim-check penalty0.000
Total, as published0.704

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 #22 on Rubric, 11 Nov 2026
<a href="https://rubric.hrih.si/editions/2026-11-11/22/"><img src="https://rubric.hrih.si/badge/2026-11-11/22.svg" alt="Ranked #22 on Rubric, 11 Nov 2026" width="245" height="28"></a>

Claim check

Claim check: 2 matches source · 6 no source given. Each claim is compared with the source the article itself cites; a flag is published only when both checkers agree.

  1. Matches sourceDate

    Microsoft Threat Intelligence reported on 2026-11-05 that threat actors use agentic AI tooling to find and abuse exposed secrets, searching GitHub at volume from August 2026.

    The cited source says the same thing.

    The article says

    “On 2026-11-05, Microsoft Threat Intelligence reported that threat actors use agentic AI tooling to find and abuse exposed secrets. It said this tooling searched GitHub at volume from August 2026”

    The source says

    “Starting in August 2026, Microsoft observed threat actors using an agentic AI offensive framework to submit large volumes of queries to GitHub for secrets”

    Source cited by the article: microsoft.com/en-us/security/blog/2026/11/05/threat-actors-use-agentic-ai-tooling-to-find-and-abuse-exposed-secrets

  2. No source givenNumber

    In the lab experiment, an ARTEX build with no dedicated secret-scanning code found 8 of 9 planted canaries using git and grep.

    The article gives no link or citation for it.

    The article says

    “In every run where it acted, ARTEX found 8 of the 9 canaries”

    The source says

    No source to compare with.

  3. No source givenVersion

    A static review of ARTEX v0.3.15 found no scanner, no GitHub code, and no cloud code in its published source.

    The article gives no link or citation for it.

    The article says

    “Our static review of this ARTEX build found no scanner, no GitHub code, and no cloud code in its published source (v0.3.15”

    The source says

    No source to compare with.

  4. No source givenNumber

    ARTEX began hunting for secrets within 6 to 13 seconds, even under the neutral prompt that never mentioned secrets.

    The article gives no link or citation for it.

    The article says

    “The first hunting command came 6 to 13 seconds into the task”

    The source says

    No source to compare with.

  5. No source givenCausal conclusion

    ARTEX recovered an AWS key from git history that had been deleted in the commit after it was added, in every active run.

    The article gives no link or citation for it.

    The article says

    “ARTEX recovered it from history in every active run. Deleting the file did not help”

    The source says

    No source to compare with.

  6. No source givenNumber

    Only 2 of the 9 planted canaries were in a file at HEAD.

    The article gives no link or citation for it.

    The article says

    “Only 2 of the 9 canaries sat in a file at HEAD”

    The source says

    No source to compare with.

  7. No source givenCausal conclusion

    The model refused the prompts asking it to use or validate the found credentials, so ARTEX made zero attempts to present a credential to a service; the refusal also appeared in tests without ARTEX.

    The article gives no link or citation for it.

    The article says

    “Across every scored run, there were zero attempts to present a credential to a service”

    The source says

    No source to compare with.

  8. Matches sourceNumber

    Some agentic pentesting tools (Pojun, Cybermes, Xalgorix, AIRecon) ship a scanner wired to the agent, according to a survey of 45 frameworks.

    The cited source says the same thing.

    The article says

    “Some agentic tools do ship a scanner wired to the agent (Pojun, Cybermes, Xalgorix, AIRecon), as we found surveying 45 of these frameworks”

    The source says

    “Four tools ship a real scanner wired to the agent: Pojun, Cybermes, Xalgorix and AIRecon. None contains a GitHub fetcher”

    Source cited by the article: blog.gitguardian.com/ai-pentesting-tools-beyond-artex

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 11 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 “An ARTEX build ships no secret scanner. In our lab, it found the secrets anyway”

More on Rubric

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