Propose a patch

Evidence

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

diff --git a/clickwarden/cli.py b/clickwarden/cli.py
--- a/clickwarden/cli.py
+++ b/clickwarden/cli.py
@@ -17,1 +17,0 @@
-clickwarden configure --set-key           # type the API key in the terminal (hidden input)
@@ -44,1 +43,0 @@
-p_conf.add_argument("--set-key", action="store_true", help="enter the API key in the terminal (hidden input)")
diff --git a/tests/test_workflows.py b/tests/test_workflows.py
--- a/tests/test_workflows.py
+++ b/tests/test_workflows.py
@@ -54,1 +54,0 @@
-for url in ('javascript:alert(1)', 'file:///C:/a', 'https://u:[email protected]',

Zero-context hunks: apply with git apply --unidiff-zero fix.patch on the tagged source of r1. 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: clickwarden: Prompting user to enter sensitive credentials (KillerSkills verdict caution 63)

## What the honeypot observed
KillerSkills ran **clickwarden@r1** in an isolated sandbox (decoy credentials, recording proxy, syscall trace; engine 1.7) and scored it **CAUTION 63/100**. Summary: no network, touches nothing outside the project, writes no memory.

- See the findings below.

Full trace and findings: https://killerskills.ai/skills/glama/clickwarden/r1

## Findings with a location
- `clickwarden/cli.py:17` · Prompting user to enter sensitive credentials — clickwarden/cli.py:17 · Prompting user to enter sensitive credentials — social engineering
- `clickwarden/cli.py:44` · Prompting user to enter sensitive credentials — clickwarden/cli.py:44 · Prompting user to enter sensitive credentials — social engineering
- `tests/test_workflows.py:54` · URL with embedded credentials — tests/test_workflows.py:54 · 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._