Propose a patch

Evidence

The sandbox observed nothing beyond the static findings; the proposal cites those.

diff --git a/tests/fixtures/category-ekonomi.html b/tests/fixtures/category-ekonomi.html
--- a/tests/fixtures/category-ekonomi.html
+++ b/tests/fixtures/category-ekonomi.html
@@ -1480,1 +1480,0 @@
-…/ld+json"> {"@context":"https://schema.org","@type":"ItemList","url":"https://www.sozcu.com.tr/ekonomi","itemListElement":[{"@type":"ListItem","position":1,"url":"https://www.sozcu.com.tr/turkiye-de-cok-sat…
diff --git a/tests/fixtures/category-gundem.html b/tests/fixtures/category-gundem.html
--- a/tests/fixtures/category-gundem.html
+++ b/tests/fixtures/category-gundem.html
@@ -1480,1 +1480,0 @@
-…/ld+json"> {"@context":"https://schema.org","@type":"ItemList","url":"https://www.sozcu.com.tr/gundem","itemListElement":[{"@type":"ListItem","position":1,"url":"https://www.sozcu.com.tr/bit-pazarindan-aya…
diff --git a/tests/fixtures/article.html b/tests/fixtures/article.html
--- a/tests/fixtures/article.html
+++ b/tests/fixtures/article.html
@@ -1025,1 +1025,0 @@
-<link rel="stylesheet" href="https://fonts.googleapis.com/css2?family=Inter:wght@400;700&display=swap">
@@ -1649,1 +1648,0 @@
-…adcrumbList","itemListElement":[{"@type":"ListItem","position":1,"item":{"@id":"https://www.sozcu.com.tr","name":"Anasayfa"}},{"@type":"ListItem","position":2,"item":{"@id":"https://www.sozcu.com.tr/gundem","n…
@@ -1652,1 +1650,0 @@
-…/schema.org","@type":"NewsArticle","mainEntityOfPage":{"@type":"WebPage","@id":"https://www.sozcu.com.tr/10-meslek-grubu-icin-yesil-pasaport-meclis-yolunda-p376844"},"url":"https://www.sozcu.com.tr/10-meslek-grubu-icin-yesil-pasaport-meclis-yolunda-p376844","@id":"https://www.sozcu.com.tr/10-meslek-grubu-icin-yesil-pasaport-meclis-yolunda…

Zero-context hunks: apply with git apply --unidiff-zero fix.patch on the tagged source of 0.1.0. If the behavior is intended, declare it (host under permissions.network, a line in the README) instead of removing it; the next crawl scores declarations.

Issue / PR body

Title: sozcu-mcp: URL with embedded credentials (KillerSkills verdict caution 60)

## What the honeypot observed
KillerSkills ran **[email protected]** in an isolated sandbox (decoy credentials, recording proxy, syscall trace; engine 1.8.1) and scored it **CAUTION 60/100**. Summary: static analysis only — behavior not yet observed.

- See the findings below.

Full trace and findings: https://killerskills.ai/skills/glama/sozcu-mcp/0.1.0

## Findings with a location
- `tests/fixtures/category-ekonomi.html:1480` · URL with embedded credentials — tests/fixtures/category-ekonomi.html:1480 · URL with embedded credentials — may be phishing or credential leaking
- `tests/fixtures/category-gundem.html:1480` · URL with embedded credentials — tests/fixtures/category-gundem.html:1480 · URL with embedded credentials — may be phishing or credential leaking
- `tests/fixtures/article.html:1025` · URL with embedded credentials — tests/fixtures/article.html:1025 · URL with embedded credentials — may be phishing or credential leaking
- `tests/fixtures/article.html:1652` · URL with embedded credentials — tests/fixtures/article.html:1652 · URL with embedded credentials — may be phishing or credential leaking
- `tests/fixtures/article.html:1649` · URL with embedded credentials — tests/fixtures/article.html:1649 · URL with embedded credentials — may be phishing or credential leaking

## Proposed change
The attached patch removes the 5 lines above. If the behavior is intended, the fix is to declare it instead: list the host under `permissions.network` (or the MCP manifest) and say in the README why the package needs it; the next crawl will re-score it with the declaration taken into account.

## How this will be verified
Nothing is "verified safe" by assertion. When a new version is published, KillerSkills re-runs it in the honeypot and the verdict page updates; you can trigger it early from the verdict page ("Re-scan after I publish a fix"). Reply here or at [email protected] if you believe the verdict is wrong; disputes are reviewed by a person and the outcome is published on the verdict page.

_Proposed through killerskills.ai/threats by a user of the package, under their own GitHub account. The evidence is public; the package was never modified by KillerSkills._