Propose a patch

Evidence

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

diff --git a/scripts/gh_reconcile.py b/scripts/gh_reconcile.py
--- a/scripts/gh_reconcile.py
+++ b/scripts/gh_reconcile.py
@@ -44,1 +44,0 @@
-HOSTS_YML = Path(os.path.expanduser("~/.config/gh/hosts.yml"))
@@ -58,1 +57,0 @@
-"""Extract token from ~/.config/gh/hosts.yml."""
diff --git a/scripts/check_issues.py b/scripts/check_issues.py
--- a/scripts/check_issues.py
+++ b/scripts/check_issues.py
@@ -24,1 +24,0 @@
-# For local runs, falls back to ~/.config/gh/hosts.yml

Zero-context hunks: apply with git apply --unidiff-zero fix.patch on the tagged source of 0.4.0. 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: lorekeeper-mcp: References a credential file in the home directory (KillerSkills verdict caution 63)

## 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 63/100**. Summary: no network, touches nothing outside the project, writes no memory.

- See the findings below.

Full trace and findings: https://killerskills.ai/skills/pypi/lorekeeper-mcp/0.4.0

## Findings with a location
- `scripts/gh_reconcile.py:44` · References a credential file in the home directory — scripts/gh_reconcile.py:44 · References a credential file in the home directory
- `scripts/gh_reconcile.py:58` · References a credential file in the home directory — scripts/gh_reconcile.py:58 · References a credential file in the home directory
- `scripts/check_issues.py:24` · References a credential file in the home directory — scripts/check_issues.py:24 · 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._