Propose a patch

Evidence

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

diff --git a/test/config.test.ts b/test/config.test.ts
--- a/test/config.test.ts
+++ b/test/config.test.ts
@@ -48,1 +48,0 @@
-expect(refusal({ PROXMOX_URL: 'https://user:[email protected]' }).type).toBe('config_error');
diff --git a/src/proxmox/redact.ts b/src/proxmox/redact.ts
--- a/src/proxmox/redact.ts
+++ b/src/proxmox/redact.ts
@@ -63,1 +63,0 @@
-/** http://user:password@proxy: /cluster/options and storage URLs can hold this. */
diff --git a/test/redact-params.test.ts b/test/redact-params.test.ts
--- a/test/redact-params.test.ts
+++ b/test/redact-params.test.ts
@@ -59,1 +59,0 @@
-expect(scrubText('http_proxy: http://user:pw@proxy:3128/x')).toBe(`http_proxy: http://${REDACTED}@proxy:3128/x`);

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: pvemcp: 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 1.7) 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/glama/pvemcp/0.1.0

## Findings with a location
- `test/config.test.ts:48` · URL with embedded credentials — test/config.test.ts:48 · URL with embedded credentials — may be phishing or credential leaking
- `src/proxmox/redact.ts:63` · URL with embedded credentials — src/proxmox/redact.ts:63 · URL with embedded credentials — may be phishing or credential leaking
- `test/redact-params.test.ts:59` · URL with embedded credentials — test/redact-params.test.ts:59 · 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._