Propose a patch

Evidence

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

diff --git a/_models.py b/_models.py
--- a/_models.py
+++ b/_models.py
@@ -1641,1 +1641,0 @@
-…ey: str | None = Field(default=None, description="Remote server SSH host key in OpenSSH format (as would appear in ~/.ssh/known_hosts). When provided, the server's host key must match exactly.") se…
@@ -1685,1 +1684,0 @@
-server_host_key: str | None = Field(default=None, description="SSH host key in OpenSSH format (as would appear in ~/.ssh/known_hosts). If provided, the server host key must match exactly.")
diff --git a/server.py b/server.py
--- a/server.py
+++ b/server.py
@@ -8430,1 +8430,0 @@
-server_host_key: str | None = Field(None, description="Remote server SSH host key in OpenSSH format (as would appear in ~/.ssh/known_hosts). When provided, the server's host key must match exactly."),
@@ -8553,1 +8552,0 @@
-server_host_key: str | None = Field(None, description="SSH host key in OpenSSH format (as would appear in ~/.ssh/known_hosts). If provided, the server host key must match exactly."),

Zero-context hunks: apply with git apply --unidiff-zero fix.patch on the tagged source of 1.0.3. 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: mcparmory-files-com: Reads credential paths from the home directory (KillerSkills verdict caution 73)

## 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 73/100**. Summary: no network, touches nothing outside the project, writes no memory.

- See the findings below.

Full trace and findings: https://killerskills.ai/skills/pypi/mcparmory-files-com/1.0.3

## Findings with a location
- `_models.py:1685` · Reads credential paths from the home directory — _models.py:1685 · Reads credential paths from the home directory
- `server.py:8430` · Reads credential paths from the home directory — server.py:8430 · Reads credential paths from the home directory
- `server.py:8553` · Reads credential paths from the home directory — server.py:8553 · Reads credential paths from the home directory
- `_models.py:1641` · Reads credential paths from the home directory — _models.py:1641 · Reads credential paths from the home directory

## 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._