Propose a patch

Evidence

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

diff --git a/lib/mcp/secret-guard.js b/lib/mcp/secret-guard.js
--- a/lib/mcp/secret-guard.js
+++ b/lib/mcp/secret-guard.js
@@ -17,1 +17,0 @@
-// 的话，`https://user:pass@host/mcp`（Basic-Auth 形态）与 `https://host/mcp#access_token=…`
@@ -129,1 +128,0 @@
-* "这条 URL 是打码形态 ⇒ 不能写回盘"。只判查询串的话，`https://user:pass@host/mcp`
@@ -198,1 +196,0 @@
-* 只替换 `search` 的话，`https://user:pass@host/mcp` 与 `https://host/mcp#access_token=…`
diff --git a/lib/compat/probe.js b/lib/compat/probe.js
--- a/lib/compat/probe.js
+++ b/lib/compat/probe.js
@@ -1013,1 +1013,0 @@
-* `npm_config_cache`、`~/.npmrc` 的 `cache=`、`%LOCALAPPDATA%\npm-cache` —— probe 全程同步，
diff --git a/lib/update-check.js b/lib/update-check.js
--- a/lib/update-check.js
+++ b/lib/update-check.js
@@ -62,1 +62,0 @@
-// 凭据走 ~/.npmrc（宿主安装器的口径），不跟着地址进缓存与界面。

Zero-context hunks: apply with git apply --unidiff-zero fix.patch on the tagged source of 0.22.8. 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: dsh-plugin-tool-management: URL with embedded credentials (KillerSkills verdict caution 68)

## 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 68/100**. Summary: no network, touches nothing outside the project, writes no memory.

- See the findings below.

Full trace and findings: https://killerskills.ai/skills/npm/dsh-plugin-tool-management/0.22.8

## Findings with a location
- `lib/mcp/secret-guard.js:17` · URL with embedded credentials — lib/mcp/secret-guard.js:17 · URL with embedded credentials — may be phishing or credential leaking
- `lib/mcp/secret-guard.js:129` · URL with embedded credentials — lib/mcp/secret-guard.js:129 · URL with embedded credentials — may be phishing or credential leaking
- `lib/compat/probe.js:1013` · References a credential file in the home directory — lib/compat/probe.js:1013 · References a credential file in the home directory
- `lib/mcp/secret-guard.js:198` · URL with embedded credentials — lib/mcp/secret-guard.js:198 · URL with embedded credentials — may be phishing or credential leaking
- `lib/update-check.js:62` · References a credential file in the home directory — lib/update-check.js:62 · References a credential file in the home directory

## 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._