Propose a patch

Evidence

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

diff --git a/tests/test_sandbox_runner.py b/tests/test_sandbox_runner.py
--- a/tests/test_sandbox_runner.py
+++ b/tests/test_sandbox_runner.py
@@ -492,1 +492,0 @@
-"~", "/", "~/.ssh", "~/.aws/credentials", "~/.config", "~/Library/Keychains",
@@ -494,1 +493,0 @@
-"~/Library", "~/Library/Group Containers", "~/.legwork.env", "~/.zsh_history", "~/.npmrc",
diff --git a/tests/test_hub.py b/tests/test_hub.py
--- a/tests/test_hub.py
+++ b/tests/test_hub.py
@@ -142,1 +142,0 @@
-result, text = call(h, "install_tool", {"repo": "owner/repo", "allow_read": ["~/.ssh"]})
diff --git a/tests/test_denials.py b/tests/test_denials.py
--- a/tests/test_denials.py
+++ b/tests/test_denials.py
@@ -24,1 +24,0 @@
-("file-read-data", f"{HOME}/.ssh/id_ed25519", "reading ~/.ssh/id_ed25519"),

Zero-context hunks: apply with git apply --unidiff-zero fix.patch on the tagged source of 0.7.19. 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: legwork-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 1.6) 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/legwork-mcp/0.7.19

## Findings with a location
- `tests/test_sandbox_runner.py:494` · References a credential file in the home directory — tests/test_sandbox_runner.py:494 · References a credential file in the home directory
- `tests/test_hub.py:142` · Reads credential paths from the home directory — tests/test_hub.py:142 · Reads credential paths from the home directory
- `tests/test_sandbox_runner.py:492` · References a credential file in the home directory — tests/test_sandbox_runner.py:492 · References a credential file in the home directory
- `tests/test_denials.py:24` · References a credential file in the home directory — tests/test_denials.py:24 · References a credential file in the home directory
- `tests/test_denials.py:24` · Reads credential paths from the home directory — tests/test_denials.py:24 · 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._