Propose a patch

Evidence

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

diff --git a/.planning/PROJECT.md b/.planning/PROJECT.md
--- a/.planning/PROJECT.md
+++ b/.planning/PROJECT.md
@@ -45,1 +45,0 @@
-Current scope, in the order the phases run.
diff --git a/macos_apps_mcp/doctor.py b/macos_apps_mcp/doctor.py
--- a/macos_apps_mcp/doctor.py
+++ b/macos_apps_mcp/doctor.py
@@ -35,1 +35,0 @@
-# Part of the add-an-adapter checklist (CLAUDE.md "Architecture"): a new

Zero-context hunks: apply with git apply --unidiff-zero fix.patch on the tagged source of 0.15.1. 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: macos-apps-mcp: HTML comment carrying imperative instructions to the agent (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/macos-apps-mcp/0.15.1

## Findings with a location
- `.planning/PROJECT.md:45` · HTML comment carrying imperative instructions to the agent — .planning/PROJECT.md:45 · HTML comment carrying imperative instructions to the agent
- `macos_apps_mcp/doctor.py:35` · Instructs the agent to modify its persistent memory or instruction files — macos_apps_mcp/doctor.py:35 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file

## 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._