Propose a patch

Evidence

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

diff --git a/src/templates/production_template/openproducer/blueprint.md b/src/templates/production_template/openproducer/blueprint.md
--- a/src/templates/production_template/openproducer/blueprint.md
+++ b/src/templates/production_template/openproducer/blueprint.md
@@ -3,1 +3,0 @@
-This file is the internal brain memory of OpenProducer (./openproducer/blueprint.md). It is ONLY written/updated during /opp-propose, /opp-sync, or /opp-produce
diff --git a/dist/templates/production_template/openproducer/blueprint.md b/dist/templates/production_template/openproducer/blueprint.md
--- a/dist/templates/production_template/openproducer/blueprint.md
+++ b/dist/templates/production_template/openproducer/blueprint.md
@@ -3,1 +3,0 @@
-This file is the internal brain memory of OpenProducer (./openproducer/blueprint.md). It is ONLY written/updated during /opp-propose, /opp-sync, or /opp-produce
diff --git a/dist/commands/update.js b/dist/commands/update.js
--- a/dist/commands/update.js
+++ b/dist/commands/update.js
@@ -96,1 +96,0 @@
-// 3. Update root specifications (STRUCTURE.md & AGENTS.md)

Zero-context hunks: apply with git apply --unidiff-zero fix.patch on the tagged source of 1.2.2. 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: openproducer: HTML comment carrying imperative instructions to the agent (KillerSkills verdict caution 78)

## 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 78/100**. Summary: no network, touches nothing outside the project, writes no memory.

- See the findings below.

Full trace and findings: https://killerskills.ai/skills/npm/openproducer/1.2.2

## Findings with a location
- `src/templates/production_template/openproducer/blueprint.md:3` · HTML comment carrying imperative instructions to the agent — src/templates/production_template/openproducer/blueprint.md:3 · HTML comment carrying imperative instructions to the agent
- `dist/templates/production_template/openproducer/blueprint.md:3` · HTML comment carrying imperative instructions to the agent — dist/templates/production_template/openproducer/blueprint.md:3 · HTML comment carrying imperative instructions to the agent
- `dist/commands/update.js:96` · Instructs the agent to modify its persistent memory or instruction files — dist/commands/update.js:96 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file

## 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._