Propose a patch

Evidence

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

diff --git a/README.md b/README.md
--- a/README.md
+++ b/README.md
@@ -212,1 +212,0 @@
-<summary><code>execute_sql</code> — Run SQL queries</summary> Execute any SQL query on the connected PostgreSQL database. | Parameter | Type | Required | Descri
@@ -263,1 +262,0 @@
-<summary><code>smart_query</code> — AI-powered query assistant</summary> Returns the public schema's tables and columns as context for answering a question. It 
@@ -275,1 +273,0 @@
-<summary><code>explain_query</code> — Execution plan analysis</summary> Show the EXPLAIN plan for a SQL query. | Parameter | Type | Required | Description | |--

Zero-context hunks: apply with git apply --unidiff-zero fix.patch on the tagged source of 2.0.0. 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: mapeg-postgres-mcp: Collapsed <details> block carrying instructions (KillerSkills verdict caution 79)

## 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 79/100**. Summary: no network, touches nothing outside the project, writes no memory.

- See the findings below.

Full trace and findings: https://killerskills.ai/skills/pypi/mapeg-postgres-mcp/2.0.0

## Findings with a location
- `README.md:212` · Collapsed <details> block carrying instructions — README.md:212 · Collapsed <details> block carrying instructions
- `README.md:275` · Collapsed <details> block carrying instructions — README.md:275 · Collapsed <details> block carrying instructions
- `README.md:263` · Collapsed <details> block carrying instructions — README.md:263 · Collapsed <details> block carrying instructions

## 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._