Propose a patch

Evidence

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

diff --git a/skills/docker-setup/SKILL.md b/skills/docker-setup/SKILL.md
--- a/skills/docker-setup/SKILL.md
+++ b/skills/docker-setup/SKILL.md
@@ -35,1 +35,0 @@
-1. **Port and key**: the server does not read `~/.ssh/config`. If the user already connects with `ssh`, get the real values with `ssh -G <alias-or-host> | grep -iE '^(hostname|port|user|identityfile) 
@@ -38,1 +37,0 @@
-4. **Host key**: the server only trusts hosts already in `~/.ssh/known_hosts`. For a non-default port the entry is under `[host]:port`: check with `ssh-keygen -F '[host]:port'`. If missing, the user c

Zero-context hunks: apply with git apply --unidiff-zero fix.patch on the tagged source of 0.1.1. 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: mcp-server-docker: Reads credential paths from the home directory (KillerSkills verdict caution 55)

## 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 55/100**. Summary: static analysis only — behavior not yet observed.

- See the findings below.

Full trace and findings: https://killerskills.ai/skills/glama/mcp-server-docker/0.1.1

## Findings with a location
- `skills/docker-setup/SKILL.md:35` · Reads credential paths from the home directory — skills/docker-setup/SKILL.md:35 · Reads credential paths from the home directory
- `skills/docker-setup/SKILL.md:38` · Reads credential paths from the home directory — skills/docker-setup/SKILL.md:38 · Reads credential paths from the home directory

## Proposed change
The attached patch removes the 2 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._