Propose a patch

Evidence

• Read ~/.ssh2mcp-token in the decoy home directory.

diff --git a/restart.sh b/restart.sh
--- a/restart.sh
+++ b/restart.sh
@@ -23,1 +23,0 @@
-curl -fsS -m 5 -H "Authorization: Bearer $(cat "$HOME/.ssh2mcp-token")" "http://127.0.0.1:$PORT/status" && echo
diff --git a/e2e-test.py b/e2e-test.py
--- a/e2e-test.py
+++ b/e2e-test.py
@@ -11,1 +11,0 @@
-TOKEN = open(os.path.expanduser("~/.ssh2mcp-token")).read().strip()
diff --git a/smoke-test.py b/smoke-test.py
--- a/smoke-test.py
+++ b/smoke-test.py
@@ -11,1 +11,0 @@
-TOKEN = open(os.path.expanduser("~/.ssh2mcp-token")).read().strip()

Zero-context hunks: apply with git apply --unidiff-zero fix.patch on the tagged source of 1.0.0. 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: ssh2mcp: Read ~/.ssh2mcp-token in the decoy home directory (KillerSkills verdict blocked 41)

## 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 **BLOCKED 41/100**. Summary: reads credential files.

- Read ~/.ssh2mcp-token in the decoy home directory.

Full trace and findings: https://killerskills.ai/skills/glama/ssh2mcp/1.0.0

## Findings with a location
- `restart.sh:23` · Reads credential paths from the home directory — restart.sh:23 · Reads credential paths from the home directory
- `e2e-test.py:11` · Reads credential paths from the home directory — e2e-test.py:11 · Reads credential paths from the home directory
- `smoke-test.py:11` · Reads credential paths from the home directory — smoke-test.py:11 · Reads credential paths from 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._