How to block the Claude Code email leak
Comments on “How to block the Claude Code email leak”
Claim-checked. Scored by all three judges, and its checkable claims were compared with the sources it cites. How far stories are checked
Claude Code put the signed-in account's email in the model's context, and the model sometimes used it as the contact in User-Agent headers of curl calls it wrote. Anthropic says a release expected early next week removes it. The interim cc-plugin-privacy mod, per AI News Report's reading of its source, checks only Bash, PowerShell and Monitor calls, so web tools, scripts and other headers pass. Some users say it did not fire on 2.1.317 and 2.1.318, and npm stable (2.1.311) has no mod. A PreToolUse hook can block it.
Why it ranked
No. 13 of 107 with a score of 0.70. The panel rated it highest on new information (0.89) and practical relevance (0.86), lowest on audience breadth (0.50). Placed No. 13, No. 7 by score alone: the sixth Security story of the day (−0.060). The placement terms move stories; they are not part of the score.
- AI judgeJudge 2claude-haiku-5-5
- Practical privacy leak in a widely used AI coding tool, with source-level analysis, a scan script and a tested hook; some claims conflict and fix is pending, so moderate substantiation and significance.
- AI judgeJudge 3gpt-5.6-luna
- A timely, technically detailed privacy incident with source-based analysis, reproducible scans, and mitigations. It is highly actionable for Claude Code users, though scope and causation remain partly unverified and some claims rely on user reports.
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
- Significance0.56
- Reader interest0.82
- Audience breadth0.50
- Practical relevance0.86
- Substantiated0.80
- Technical depth0.84
- New information0.89
- Counts against: Promotional0.04
- Counts against: Overclaim0.19
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? | 0.55 | 0.45 | 0.70 | 0.56 | 0.25 | +0.24 | +0.136 |
| Reader interestWould a well-informed senior engineer or tech founder want to read this today, and likely pass it on? | 0.75 | 0.80 | 0.92 | 0.82 | 0.17 | +0.26 | +0.214 |
| Audience breadthHow many people who build technology does it concern? | 0.29 | 0.55 | 0.65 | 0.50 | 0.36 | +0.13 | +0.065 |
| Practical relevanceHow useful is it to someone who builds software or tech products? | 0.93 | 0.80 | 0.86 | 0.86 | 0.13 | +0.22 | +0.190 |
| 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. | 0.89 | 0.70 | 0.82 | 0.80 | 0.19 | +0.05 | +0.040 |
| Technical depthHow technically substantive is it? | 1.00 | 0.80 | 0.72 | 0.84 | 0.28 | +0.05 | +0.042 |
| New informationDoes it contain information absent from the stories covered in the last 7 days (list provided)? | 0.83 | 0.90 | 0.93 | 0.89 | 0.10 | +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 | 0.02 | 0.04 | 0.03 | −0.19 | −0.007 |
| OverclaimDo the headline or conclusions claim more than the body supports? | 0.20 | 0.20 | 0.18 | 0.19 | 0.02 | −0.11 | −0.021 |
| Sum of contributions | +0.702 | ||||||
| Claim-check penalty | 0.000 | ||||||
| Total, as published | 0.702 | ||||||
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/2026-11-07/13/"><img src="https://rubric.hrih.si/badge/2026-11-07/13.svg" alt="Ranked #13 on Rubric, 7 Nov 2026" width="238" height="28"></a>Claim check
Claim check: 3 matches source · 4 no source given · 1 couldn’t check. Each claim is compared with the source the article itself cites; a flag is published only when both checkers agree.
Matches sourceDate
A user opened issue 107757 on the Claude Code GitHub repository on November 5, 2026 at 22:13 UTC, reporting that Claude Code 2.1.318 on macOS put their email address in the User-Agent header of web requests.
The cited source says the same thing.
The article says “On November 5, 2026 at 22:13 UTC, a user opened issue 107757 on the Claude Code GitHub repository”
The source says “opened 2026-11-05 by taylor-edwards”
Source cited by the article: github.com/anthropics/claude-code/issues/107757
Couldn’t checkNumber
By the morning of November 6 the GitHub issue had more than 750 reactions and 87 comments, and its Hacker News thread passed 1,390 points.
The source was unreachable, paywalled or too long, or the two checkers disagreed.
The article says “By the morning of November 6 the issue had more than 750 reactions and 87 comments, and its Hacker News thread passed 1,390 points”
The source says No passage could be compared.
Source cited by the article: github.com/anthropics/claude-code/issues/107757
Matches sourceQuote
Lydia Hallie of the Claude Code team wrote on Hacker News that the team is removing the account email from the context given to the model, in a release expected early next week.
The cited source says the same thing.
The article says “the team is removing the account email from the context Claude Code gives the model, in a release expected early next week, and apologized”
The source says “We're removing the account email address from the context Claude Code gives the model. This update will hit Claude Code users in the next release, which should arrive early next…”
Source cited by the article: news.ycombinator.com/item
Matches sourceCausal conclusion
Claude Code began giving the model the signed-in account's email because users had reported Claude making up names in places like @author tags; the model then sometimes used it as the User-Agent contact.
The cited source says the same thing.
The article says “users had reported Claude making up names in places like @author tags, so Claude Code began giving the model the signed-in account's email”
The source says “Users had reported Claude would hallucinate names for things like @author tags, since it didn't have context on the account. So we added the account email in the model's context…”
Source cited by the article: news.ycombinator.com/item
No source givenNumber
The cc-plugin-privacy mod runs only for Bash, PowerShell and Monitor and refuses a call only when its input holds the account address and names a User-Agent.
The article gives no link or citation for it.
The article says “It refuses the call when the input holds the address AND names a User-Agent”
The source says No source to compare with.
No source givenQuote
The mod's README says WebFetch, WebSearch and every MCP tool are not checked, and that it is a courtesy, not a boundary.
The article gives no link or citation for it.
The article says “WebFetch, WebSearch and every MCP tool. None are checked”
The source says No source to compare with.
No source givenVersion
On November 6 the npm stable tag was 2.1.311, latest was 2.1.318 and next was 2.1.319, and 2.1.317 was published on November 2.
The article gives no link or citation for it.
The article says “the stable tag is 2.1.311, latest is 2.1.318, and next is 2.1.319. 2.1.317 was published on November 2”
The source says No source to compare with.
No source givenNumber
One commenter reported 53 calls across 8 sessions that put his address in a User-Agent, almost all from subagents writing their own curl -A lines.
The article gives no link or citation for it.
The article says “reported 53 calls across 8 sessions that put his address in a User-Agent, almost all from subagents writing their own curl -A lines”
The source says No source to compare with.
Also covered by
No other coverage was clustered with this story.
Elsewhere
Elsewhere: HN 2 pts, not on front page
Recorded for context only, checked 7 Nov 2026, 05:47 UTC. It played no part in the ranking.