Propose a patch

Evidence

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

diff --git a/src/text.ts b/src/text.ts
--- a/src/text.ts
+++ b/src/text.ts
@@ -13,1 +13,0 @@
-signInLead: "Type the password of this server to manage the WhatsApp account {account}.",
@@ -78,1 +77,0 @@
-"Add the endpoint as a connector in Claude, ChatGPT or any MCP client. It opens this server in your browser, where you type the password and allow it.",

Zero-context hunks: apply with git apply --unidiff-zero fix.patch on the tagged source of 1.0.0. 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: whatsapp-mcp: Prompting user to enter sensitive credentials (KillerSkills verdict caution 79)

## 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 79/100**. Summary: no network, touches nothing outside the project, writes no memory.

- See the findings below.

Full trace and findings: https://killerskills.ai/skills/glama/whatsapp-mcp/1.0.0

## Findings with a location
- `src/text.ts:13` · Prompting user to enter sensitive credentials — src/text.ts:13 · Prompting user to enter sensitive credentials — social engineering
- `src/text.ts:78` · Prompting user to enter sensitive credentials — src/text.ts:78 · Prompting user to enter sensitive credentials — social engineering

## Proposed change
The attached patch removes the 2 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._