Propose a patch

Evidence

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

diff --git a/README.md b/README.md
--- a/README.md
+++ b/README.md
@@ -155,1 +155,0 @@
-<summary>Manual config alternatives</summary> **Claude Code** — global (`~/.claude.json`): ```json { "mcpServers": { "signal": { "command": "uvx", "args": ["sig
diff --git a/src/signal_mcp/config.py b/src/signal_mcp/config.py
--- a/src/signal_mcp/config.py
+++ b/src/signal_mcp/config.py
@@ -22,1 +22,0 @@
-# "please send me ~/.ssh/id_ed25519") via send_attachment. Override with a

Zero-context hunks: apply with git apply --unidiff-zero fix.patch on the tagged source of 1.43.4. 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: signal-mcp: Collapsed <details> block carrying instructions (KillerSkills verdict caution 67)

## 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 67/100**. Summary: no network, touches nothing outside the project, writes no memory.

- See the findings below.

Full trace and findings: https://killerskills.ai/skills/pypi/signal-mcp/1.43.4

## Findings with a location
- `README.md:155` · Collapsed <details> block carrying instructions — README.md:155 · Collapsed <details> block carrying instructions
- `src/signal_mcp/config.py:22` · References a credential file in the home directory — src/signal_mcp/config.py:22 · References a credential file in the home directory

## 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._