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
@@ -129,1 +129,0 @@
-<summary>Cursor</summary> Add to `.cursor/mcp.json` (or use the `.mcp.json` at the repo root for local dev): ```json { "mcpServers": { "kubeflow": { "command": 
@@ -197,1 +196,0 @@
-<summary> HTTP Authentication</summary> When using `--transport http`, configure auth to secure the endpoint: ```bash # Simple API key (dev/staging) kubeflow-mc
diff --git a/AGENTS.md b/AGENTS.md
--- a/AGENTS.md
+++ b/AGENTS.md
@@ -159,1 +159,0 @@
-- Example titles: `feat(trainer): add wait hint`, `chore(docs): add AGENTS.md`
diff --git a/CHANGELOG/CHANGELOG-0.1.md b/CHANGELOG/CHANGELOG-0.1.md
--- a/CHANGELOG/CHANGELOG-0.1.md
+++ b/CHANGELOG/CHANGELOG-0.1.md
@@ -68,1 +68,0 @@
-- chore(docs): add AGENTS.md and Copilot review instructions ([#70](https://github.com/kubeflow/mcp-server/pull/70) by @Raghul-M)

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: kubeflow-mcp: Collapsed <details> block carrying instructions (KillerSkills verdict caution 75)

## What the honeypot observed
KillerSkills ran **[email protected]** in an isolated sandbox (decoy credentials, recording proxy, syscall trace; engine 1.5) and scored it **CAUTION 75/100**. Summary: no network, touches nothing outside the project, writes no memory.

- See the findings below.

Full trace and findings: https://killerskills.ai/skills/pypi/kubeflow-mcp/0.1.1

## Findings with a location
- `README.md:197` · Collapsed <details> block carrying instructions — README.md:197 · Collapsed <details> block carrying instructions
- `README.md:129` · Collapsed <details> block carrying instructions — README.md:129 · Collapsed <details> block carrying instructions
- `AGENTS.md:159` · Instructs the agent to modify its persistent memory or instruction files — AGENTS.md:159 · Instructs the agent to modify its persistent memory or instruction files
- `CHANGELOG/CHANGELOG-0.1.md:68` · Instructs the agent to modify its persistent memory or instruction files — CHANGELOG/CHANGELOG-0.1.md:68 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file

## Proposed change
The attached patch removes the 4 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._