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
@@ -88,1 +88,0 @@
-<summary>Run with Docker</summary> ```bash docker build -t mcp-server-qdrant . docker run -d --name mcp-qdrant \ --restart unless-stopped \ --network mcp-networ
@@ -109,1 +108,0 @@
-<summary>Auto-update with Watchtower (GHCR)</summary> ```bash # Run from GHCR (make the package public or login to GHCR first). docker run -d --name mcp-qdrant 
@@ -131,1 +129,0 @@
-<summary>Run locally (uvx)</summary> ```bash QDRANT_URL=... COLLECTION_NAME=... uvx mad-mcp-qdrant ``` Prefer `mad-mcp-qdrant`; `mcp-server-qdrant` remains as a
@@ -191,1 +188,0 @@
-<summary>Agent Navigation</summary> - `qdrant-check-configuration`: check hosted readiness, accepted headers, cache settings, and missing configuration without 
@@ -442,1 +438,0 @@
-<summary>Memory Contract</summary> Stored memories are normalized to include at least: `text`, `type`, `entities`, `source`, `created_at`, `updated_at`, `scope`

Zero-context hunks: apply with git apply --unidiff-zero fix.patch on the tagged source of 1.9.3. 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: mad-mcp-qdrant: Collapsed <details> block carrying instructions (KillerSkills verdict caution 72)

## 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 72/100**. Summary: no network, touches nothing outside the project, writes no memory.

- See the findings below.

Full trace and findings: https://killerskills.ai/skills/pypi/mad-mcp-qdrant/1.9.3

## Findings with a location
- `README.md:109` · Collapsed <details> block carrying instructions — README.md:109 · Collapsed <details> block carrying instructions
- `README.md:88` · Collapsed <details> block carrying instructions — README.md:88 · Collapsed <details> block carrying instructions
- `README.md:442` · Collapsed <details> block carrying instructions — README.md:442 · Collapsed <details> block carrying instructions
- `README.md:131` · Collapsed <details> block carrying instructions — README.md:131 · Collapsed <details> block carrying instructions
- `README.md:191` · Collapsed <details> block carrying instructions — README.md:191 · Collapsed <details> block carrying instructions

## Proposed change
The attached patch removes the 5 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._