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
@@ -218,1 +218,0 @@
-<summary><strong>Claude Code</strong></summary> Add via CLI: ```bash claude mcp add linkwarden --env LINKWARDEN_API_URL=https://links.example.com --env LINKWARD
@@ -246,1 +245,0 @@
-<summary><strong>VS Code / GitHub Copilot</strong></summary> Create [`.vscode/mcp.json`](.vscode/mcp.json) in the project root: ```json { "servers": { "linkward
@@ -289,1 +287,0 @@
-<summary><strong>Windsurf</strong></summary> Edit `~/.codeium/windsurf/mcp_config.json` (macOS/Linux) or the Windsurf MCP settings UI: ```json { "mcpServers": {
@@ -313,1 +310,0 @@
-<summary><strong>Zed</strong></summary> Add under `context_servers` in Zed `settings.json` (Agent Panel → settings also works): ```json { "context_servers": { "
@@ -335,1 +331,0 @@
-<summary><strong>Cline</strong></summary> Edit the Cline MCP settings file (`cline_mcp_settings.json` via the Cline MCP UI): ```json { "mcpServers": { "linkward
@@ -357,1 +352,0 @@
-<summary><strong>Continue</strong></summary> In `.continue/config.yaml`: ```yaml mcpServers: - name: linkwarden command: uvx args: - linkwarden-mcp env: LINKWAR
@@ -375,1 +369,0 @@
-<summary><strong>Generic / any stdio MCP host</strong></summary> Any host that can spawn a stdio MCP server: | Field | Value | |-------|-------| | Command | `uv

Zero-context hunks: apply with git apply --unidiff-zero fix.patch on the tagged source of 0.1.6. 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: linkwarden-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/linkwarden-mcp/0.1.6

## Findings with a location
- `README.md:289` · Collapsed <details> block carrying instructions — README.md:289 · Collapsed <details> block carrying instructions
- `README.md:313` · Collapsed <details> block carrying instructions — README.md:313 · Collapsed <details> block carrying instructions
- `README.md:218` · Collapsed <details> block carrying instructions — README.md:218 · Collapsed <details> block carrying instructions
- `README.md:246` · Collapsed <details> block carrying instructions — README.md:246 · Collapsed <details> block carrying instructions
- `README.md:357` · Collapsed <details> block carrying instructions — README.md:357 · Collapsed <details> block carrying instructions
- `README.md:375` · Collapsed <details> block carrying instructions — README.md:375 · Collapsed <details> block carrying instructions
- `README.md:335` · Collapsed <details> block carrying instructions — README.md:335 · Collapsed <details> block carrying instructions

## Proposed change
The attached patch removes the 7 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._