Propose a patch

Evidence

The sandbox observed nothing beyond the static findings; the proposal cites those.

diff --git a/src/mcp_agent_mail/templates/mail_thread.html b/src/mcp_agent_mail/templates/mail_thread.html
--- a/src/mcp_agent_mail/templates/mail_thread.html
+++ b/src/mcp_agent_mail/templates/mail_thread.html
@@ -62,1 +62,0 @@
-Message Header (Always Visible)
diff --git a/src/mcp_agent_mail/cli.py b/src/mcp_agent_mail/cli.py
--- a/src/mcp_agent_mail/cli.py
+++ b/src/mcp_agent_mail/cli.py
@@ -3982,1 +3982,0 @@
-"""Detect AGENTS.md/CLAUDE.md files and append the latest Agent Mail + Beads blurbs."""
diff --git a/README.md b/README.md
--- a/README.md
+++ b/README.md
@@ -126,1 +126,0 @@
-… have the mail tool available. See below for a ready-made chunk of text you can add to the end of your existing AGENTS.md or CLAUDE.md files to help your agents better utilize the new tools. # Change port after in…
@@ -132,1 +131,0 @@
-## Ready-Made Blurb to Add to Your AGENTS.md or CLAUDE.md Files:

Zero-context hunks: apply with git apply --unidiff-zero fix.patch on the tagged source of 0.1.0. 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: mseep-mcp-agent-mail: HTML comment carrying imperative instructions to the agent (KillerSkills verdict caution 70)

## 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 70/100**. Summary: calls astral.sh only, touches nothing outside the project, writes no memory.

- See the findings below.

Full trace and findings: https://killerskills.ai/skills/pypi/mseep-mcp-agent-mail/0.1.0

## Findings with a location
- `src/mcp_agent_mail/templates/mail_thread.html:62` · HTML comment carrying imperative instructions to the agent — src/mcp_agent_mail/templates/mail_thread.html:62 · HTML comment carrying imperative instructions to the agent · informational: not an instruction file
- `src/mcp_agent_mail/cli.py:3982` · Instructs the agent to modify its persistent memory or instruction files — src/mcp_agent_mail/cli.py:3982 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file
- `README.md:126` · Instructs the agent to modify its persistent memory or instruction files — README.md:126 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file
- `README.md:132` · Instructs the agent to modify its persistent memory or instruction files — README.md:132 · 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._