Propose a patch

Evidence

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

diff --git a/mcp_client_for_ollama/utils/hil_manager.py b/mcp_client_for_ollama/utils/hil_manager.py
--- a/mcp_client_for_ollama/utils/hil_manager.py
+++ b/mcp_client_for_ollama/utils/hil_manager.py
@@ -64,1 +64,0 @@
-self.console.print("[green]🧑‍💻 HIL confirmations enabled[/green]")
@@ -107,1 +106,0 @@
-self.console.print("\n[bold yellow]🧑‍💻 Human-in-the-Loop Confirmation[/bold yellow]")
@@ -186,1 +184,0 @@
-self.console.print("[magenta]🧑‍💻 Tool calls will proceed automatically for the remainder of this session.[/magenta]")
diff --git a/mcp_client_for_ollama/prompts/handler.py b/mcp_client_for_ollama/prompts/handler.py
--- a/mcp_client_for_ollama/prompts/handler.py
+++ b/mcp_client_for_ollama/prompts/handler.py
@@ -206,1 +206,0 @@
-self.console.print("\n[bold yellow]🧑‍💻 Prompt Injection Confirmation[/bold yellow]")

Zero-context hunks: apply with git apply --unidiff-zero fix.patch on the tagged source of 0.35.1. 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: mcp-client-for-ollama: Hidden zero-width characters detected (KillerSkills verdict caution 70)

## 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 70/100**. Summary: no network, touches nothing outside the project, writes no memory.

- See the findings below.

Full trace and findings: https://killerskills.ai/skills/pypi/mcp-client-for-ollama/0.35.1

## Findings with a location
- `mcp_client_for_ollama/utils/hil_manager.py:107` · Hidden zero-width characters detected — mcp_client_for_ollama/utils/hil_manager.py:107 · Hidden zero-width characters detected — may conceal content
- `mcp_client_for_ollama/utils/hil_manager.py:64` · Hidden zero-width characters detected — mcp_client_for_ollama/utils/hil_manager.py:64 · Hidden zero-width characters detected — may conceal content
- `mcp_client_for_ollama/prompts/handler.py:206` · Hidden zero-width characters detected — mcp_client_for_ollama/prompts/handler.py:206 · Hidden zero-width characters detected — may conceal content
- `mcp_client_for_ollama/utils/hil_manager.py:186` · Hidden zero-width characters detected — mcp_client_for_ollama/utils/hil_manager.py:186 · Hidden zero-width characters detected — may conceal content

## Proposed change
The attached patch removes the 4 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._