Propose a patch

Evidence

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

diff --git a/README.md b/README.md
--- a/README.md
+++ b/README.md
@@ -79,1 +79,0 @@
-<summary>Capability comparison recorded on 2026-07-29</summary> As of 2026-07-29, the capability comparison below reflects the official [Brave MCP](https://gith
diff --git a/dist/proxy.js b/dist/proxy.js
--- a/dist/proxy.js
+++ b/dist/proxy.js
@@ -299,1 +299,0 @@
-"Please provide a valid URL (e.g., http://proxy:8080 or http://user:pass@proxy:8080)");
diff --git a/dist/resources.js b/dist/resources.js
--- a/dist/resources.js
+++ b/dist/resources.js
@@ -154,1 +154,0 @@
-…g., http://localhost:8080). For Basic Auth, embed credentials in the URL (e.g., https://user:[email protected]); percent-encode special characters in the username or passwo…

Zero-context hunks: apply with git apply --unidiff-zero fix.patch on the tagged source of 2.10.1. 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: mcp-searxng: Collapsed <details> block carrying instructions (KillerSkills verdict caution 74)

## 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 74/100**. Summary: no network, touches nothing outside the project, writes no memory.

- See the findings below.

Full trace and findings: https://killerskills.ai/skills/npm/mcp-searxng/2.10.1

## Findings with a location
- `README.md:79` · Collapsed <details> block carrying instructions — README.md:79 · Collapsed <details> block carrying instructions
- `dist/proxy.js:299` · URL with embedded credentials — dist/proxy.js:299 · URL with embedded credentials — may be phishing or credential leaking
- `dist/resources.js:154` · URL with embedded credentials — dist/resources.js:154 · URL with embedded credentials — may be phishing or credential leaking

## Proposed change
The attached patch removes the 3 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._