Propose a patch

Evidence

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

diff --git a/matmul_mcp/server.py b/matmul_mcp/server.py
--- a/matmul_mcp/server.py
+++ b/matmul_mcp/server.py
@@ -287,1 +287,0 @@
-"user for their PUBLIC key (e.g. the contents of ~/.ssh/id_ed25519.pub) "
@@ -423,1 +422,0 @@
-public_key: Annotated[str, Field(description="The PUBLIC key line, e.g. 'ssh-ed25519 AAAA... user@host' (contents of ~/.ssh/id_ed25519.pub). Never a private key.")],
@@ -429,1 +427,0 @@
-"(e.g. ~/.ssh/id_ed25519.pub).")

Zero-context hunks: apply with git apply --unidiff-zero fix.patch on the tagged source of 0.0.1. 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: matmul-mcp: References a credential file in the home directory (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/pypi/matmul-mcp/0.0.1

## Findings with a location
- `matmul_mcp/server.py:429` · References a credential file in the home directory — matmul_mcp/server.py:429 · References a credential file in the home directory
- `matmul_mcp/server.py:423` · References a credential file in the home directory — matmul_mcp/server.py:423 · References a credential file in the home directory
- `matmul_mcp/server.py:287` · References a credential file in the home directory — matmul_mcp/server.py:287 · References a credential file in the home directory

## 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._