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
@@ -441,1 +441,0 @@
-<summary>Manual Setup (if you prefer)</summary> > **Tip:** Run `nlm setup add json` for an interactive wizard that generates the right JSON snippet for your too
diff --git a/src/notebooklm_tools/cli/commands/skill.py b/src/notebooklm_tools/cli/commands/skill.py
--- a/src/notebooklm_tools/cli/commands/skill.py
+++ b/src/notebooklm_tools/cli/commands/skill.py
@@ -240,1 +240,0 @@
-"""Install/update AGENTS.md format (append with markers)."""
diff --git a/src/notebooklm_tools/data/SKILL.md b/src/notebooklm_tools/data/SKILL.md
--- a/src/notebooklm_tools/data/SKILL.md
+++ b/src/notebooklm_tools/data/SKILL.md
@@ -316,1 +316,0 @@
-# Each --slide value must be: '<slide-number> <instruction>'

Zero-context hunks: apply with git apply --unidiff-zero fix.patch on the tagged source of 1.0.8. 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: notebooklm-enterprise-mcp: Collapsed <details> block carrying instructions (KillerSkills verdict caution 77)

## What the honeypot observed
KillerSkills ran **[email protected]** in an isolated sandbox (decoy credentials, recording proxy, syscall trace; engine 1.8.1) and scored it **CAUTION 77/100**. Summary: no network, touches nothing outside the project, writes no memory.

- See the findings below.

Full trace and findings: https://killerskills.ai/skills/pypi/notebooklm-enterprise-mcp/1.0.8

## Findings with a location
- `README.md:441` · Collapsed <details> block carrying instructions — README.md:441 · Collapsed <details> block carrying instructions
- `src/notebooklm_tools/cli/commands/skill.py:240` · Instructs the agent to modify its persistent memory or instruction files — src/notebooklm_tools/cli/commands/skill.py:240 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file
- `src/notebooklm_tools/data/SKILL.md:316` · Fake instruction boundary tag — src/notebooklm_tools/data/SKILL.md:316 · Fake instruction boundary tag

## 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._