Analysis of 366,845 requests for claude.json and .cursor/mcp.json
Comments on “Analysis of 366,845 requests for claude.json and .cursor/mcp.json”
Claim-checked. Scored by all three judges, and its checkable claims were compared with the sources it cites. How far stories are checked
HoneyLabs reports that on 4 September a Google Cloud scanner added 49 paths in one second, 32 of them AI coding tool files such as Claude Code's /.claude/.credentials.json, /.cursor/mcp.json and other MCP and LiteLLM configs. It dropped them after 7 September, but other clients have kept requesting them: 8,067 requests through 9 November. The figures come from HoneyLabs honeypots alone, and the post cannot say whether any real server answered. Its advice: check web roots for exposed home directories, rotate exposed tokens, and block by path.
Why it ranked
No. 8 of 106 with a score of 0.73. The panel rated it highest on substantiated (0.90) and new information (0.88), lowest on significance (0.58). Placed No. 8, No. 6 by score alone: the fifth Security story of the day (−0.040). The placement terms move stories; they are not part of the score.
- AI judgeJudge 2claude-haiku-5-5
- Original honeypot measurement showing scanners now target AI coding assistant credential files; well-substantiated with traffic data, concrete paths, and practical checks and mitigations for builders.
- AI judgeJudge 3gpt-5.6-luna
- Detailed honeypot measurements show widespread probing for AI-tool credentials and MCP secrets, with concrete paths, scale, attribution caveats, and mitigations. It is timely, actionable security research with broad relevance to developers and operators.
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
0.73total under rubric v2.3
- Significance0.58
- Reader interest0.79
- Audience breadth0.63
- Practical relevance0.87
- Substantiated0.90
- Technical depth0.82
- New information0.88
- Counts against: Promotional0.03
- Counts against: Overclaim0.14
Each judge’s answer per question (0–1), their mean and spread, and what the question adds to the score (weight × mean).
| Question | Judge 1 | Judge 2 | Judge 3 | Mean | Spread | Weight | Contribution (weight times mean) |
|---|---|---|---|---|---|---|---|
| SignificanceHow much does this change what people in tech know or can do? | 0.60 | 0.45 | 0.68 | 0.58 | 0.23 | +0.24 | +0.139 |
| Reader interestWould a well-informed senior engineer or tech founder want to read this today, and likely pass it on? | 0.78 | 0.70 | 0.90 | 0.79 | 0.20 | +0.26 | +0.206 |
| Audience breadthHow many people who build technology does it concern? | 0.68 | 0.60 | 0.62 | 0.63 | 0.08 | +0.13 | +0.082 |
| Practical relevanceHow useful is it to someone who builds software or tech products? | 0.94 | 0.85 | 0.82 | 0.87 | 0.12 | +0.22 | +0.191 |
| 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. | 0.96 | 0.85 | 0.88 | 0.90 | 0.11 | +0.05 | +0.045 |
| Technical depthHow technically substantive is it? | 0.96 | 0.80 | 0.70 | 0.82 | 0.26 | +0.05 | +0.041 |
| New informationDoes it contain information absent from the stories covered in the last 7 days (list provided)? | 0.82 | 0.85 | 0.97 | 0.88 | 0.15 | +0.05 | +0.044 |
| 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. | 0.04 | 0.05 | 0.01 | 0.03 | 0.04 | −0.19 | −0.006 |
| OverclaimDo the headline or conclusions claim more than the body supports? | 0.19 | 0.15 | 0.08 | 0.14 | 0.11 | −0.11 | −0.015 |
| Sum of contributions | +0.727 | ||||||
| Claim-check penalty | 0.000 | ||||||
| Total, as published | 0.727 | ||||||
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.
<a href="https://rubric.hrih.si/editions/2026-11-12/8/"><img src="https://rubric.hrih.si/badge/2026-11-12/8.svg" alt="Ranked #8 on Rubric, 12 Nov 2026" width="238" height="28"></a>Claim check
Claim check: 1 matches source · 7 no source given. Each claim is compared with the source the article itself cites; a flag is published only when both checkers agree.
No source givenNumber
A Google Cloud credential scanner requested 32 AI coding assistant file paths, among 49 new paths first requested within one second on 4 September, after requesting the same 543 paths daily since 27 August.
The article gives no link or citation for it.
The article says “Nothing had been added for a week, and then 49 paths showed up within one second. Of those, 32 belong to AI coding tools”
The source says No source to compare with.
No source givenNumber
The scanner sent 366,845 requests in its first eleven days, using 2,894 addresses, of which 2,499 were seen on only one day.
The article gives no link or citation for it.
The article says “It sent 366,845 requests in that time, and it did not keep its addresses for long: of the 2,894 it used, we saw 2,499 on one day only”
The source says No source to compare with.
No source givenNumber
The scanner's wordlist went to 203 ports, and port 443 was only the 28th busiest.
The article gives no link or citation for it.
The article says “The wordlist went to 203 ports, and 443 was only the 28th busiest”
The source says No source to compare with.
No source givenNumber
Between 8 September and 9 November HoneyLabs counted 8,067 requests for the AI files, versus 18,707 in the week of 4 September alone.
The article gives no link or citation for it.
The article says “Between 8 September and 9 November we counted 8,067 requests for these files, with some in every week. For scale, the week of 4 September alone had 18,707”
The source says No source to compare with.
No source givenDate
The scanner requested the AI files on 4 to 7 September, then ran one more sweep without them on 8 September and disappeared.
The article gives no link or citation for it.
The article says “The scanner asked for the AI files on four days, 4 to 7 September. On 8 September it ran one more sweep without them and then disappeared”
The source says No source to compare with.
No source givenNumber
The crusader-worker/1.0 client shares 390 addresses with the scanner, against about 1,100 expected by chance, so the addresses give no reason to connect them.
The article gives no link or citation for it.
The article says “Two clients picking independently from that pool would overlap on about 1,100. These two share 390, so the addresses give no reason to connect them”
The source says No source to compare with.
Matches sourceDate
SANS Internet Storm Center wrote up the earliest known probes for these files in July, from two weeks of logs on a single small web host.
The cited source says the same thing.
The article says “In July, SANS Internet Storm Center wrote up the earliest probes we know, from two weeks of logs on a single small web host that ran none of these tools”
The source says “I pulled 14 days of Apache and ModSecurity logs from a single small web host”
Source cited by the article: isc.sans.edu/diary/33150
No source givenGeneralization
The scanner's list was guesswork in part, because no known tool writes /anthropic.json, /openai.json or /ai.json.
The article gives no link or citation for it.
The article says “Whoever wrote the list was also guessing, because as far as we know no tool writes /anthropic.json, /openai.json or /ai.json”
The source says No source to compare with.
Also covered by
No other coverage was clustered with this story.
Elsewhere
Elsewhere: HN 3 pts, not on front page
Recorded for context only, checked 12 Nov 2026, 05:47 UTC. It played no part in the ranking.