Propose a patch

Evidence

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

diff --git a/setup_ui.py b/setup_ui.py
--- a/setup_ui.py
+++ b/setup_ui.py
@@ -1776,1 +1776,0 @@
-if (!input.value.trim()) { setMsg(msg, "error", "Paste the API key before saving."); return; }
diff --git a/setup_audit.py b/setup_audit.py
--- a/setup_audit.py
+++ b/setup_audit.py
@@ -593,1 +593,0 @@
-f"Add a line `@AGENTS.md` to {os.path.join(project, 'CLAUDE.md')} (create the file "

Zero-context hunks: apply with git apply --unidiff-zero fix.patch on the tagged source of 0.9.71. 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: smart-tool: Prompting user to enter sensitive 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/smart-tool/0.9.71

## Findings with a location
- `setup_ui.py:1776` · Prompting user to enter sensitive credentials — setup_ui.py:1776 · Prompting user to enter sensitive credentials — social engineering
- `setup_audit.py:593` · Instructs the agent to modify its persistent memory or instruction files — setup_audit.py:593 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file

## 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._