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
@@ -334,1 +334,0 @@
-<summary><b>Working on labgrid-mcp itself</b></summary> The integration suite runs the whole stack, including the demo, against real coordinator/exporter proces
diff --git a/docs/DESIGN.md b/docs/DESIGN.md
--- a/docs/DESIGN.md
+++ b/docs/DESIGN.md
@@ -664,1 +664,0 @@
-<summary>Verification (two-client driver against a real coordinator)</summary> Verified live: bare-place acquire with no resources succeeds and propagates to a 
diff --git a/CLAUDE.md b/CLAUDE.md
--- a/CLAUDE.md
+++ b/CLAUDE.md
@@ -31,1 +31,0 @@
-Everything below is owned by this repo. /factory-update never touches it.

Zero-context hunks: apply with git apply --unidiff-zero fix.patch on the tagged source of 0.1.5. 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: labgrid-mcp: Collapsed <details> block carrying instructions (KillerSkills verdict caution 53)

## 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 53/100**. Summary: static analysis only — behavior not yet observed.

- See the findings below.

Full trace and findings: https://killerskills.ai/skills/pypi/labgrid-mcp/0.1.5

## Findings with a location
- `README.md:334` · Collapsed <details> block carrying instructions — README.md:334 · Collapsed <details> block carrying instructions
- `docs/DESIGN.md:664` · Collapsed <details> block carrying instructions — docs/DESIGN.md:664 · Collapsed <details> block carrying instructions
- `CLAUDE.md:31` · HTML comment carrying imperative instructions to the agent — CLAUDE.md:31 · HTML comment carrying imperative instructions to the agent

## 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._