Propose a patch

Evidence

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

diff --git a/tests/test_offline.py b/tests/test_offline.py
--- a/tests/test_offline.py
+++ b/tests/test_offline.py
@@ -144,1 +144,0 @@
-assert vision.classify_screen(L(('Enter your password', .1, .2), ('Password', .1, .3), ('Google', .1, .1)))['kind'] == 'password'

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: phone-agent: Prompting user to enter sensitive credentials (KillerSkills verdict caution 74)

## 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 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/glama/phone-agent/0.1.0

## Findings with a location
- `tests/test_offline.py:144` · Prompting user to enter sensitive credentials — tests/test_offline.py:144 · Prompting user to enter sensitive credentials — social engineering

## Proposed change
The attached patch removes the 1 line 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._