Propose a patch

Evidence

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

diff --git a/ISSUE_TEMPLATE.md b/ISSUE_TEMPLATE.md
--- a/ISSUE_TEMPLATE.md
+++ b/ISSUE_TEMPLATE.md
@@ -28,1 +28,0 @@
-e.g., v20.10.0 (run node --version)
@@ -29,1 +28,0 @@
-e.g., 1.8.0 (run grazer --version)
diff --git a/DEPLOY.md b/DEPLOY.md
--- a/DEPLOY.md
+++ b/DEPLOY.md
@@ -110,1 +110,0 @@
-## 7. Update CLAUDE.md
@@ -112,1 +111,0 @@
-Add to `/home/scott/CLAUDE.md`:

Zero-context hunks: apply with git apply --unidiff-zero fix.patch on the tagged source of 1.0.0. 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: grazer-skill-main: HTML comment carrying imperative instructions to the agent (KillerSkills verdict caution 53)

## What the honeypot observed
KillerSkills ran **[email protected]** in an isolated sandbox (decoy credentials, recording proxy, syscall trace; engine 1.8) 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/clawhub/grazer-skill-main/1.0.0

## Findings with a location
- `ISSUE_TEMPLATE.md:29` · HTML comment carrying imperative instructions to the agent — ISSUE_TEMPLATE.md:29 · HTML comment carrying imperative instructions to the agent
- `ISSUE_TEMPLATE.md:28` · HTML comment carrying imperative instructions to the agent — ISSUE_TEMPLATE.md:28 · HTML comment carrying imperative instructions to the agent
- `DEPLOY.md:110` · Instructs the agent to modify its persistent memory or instruction files — DEPLOY.md:110 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file · informational: not an instruction file
- `DEPLOY.md:112` · Instructs the agent to modify its persistent memory or instruction files — DEPLOY.md:112 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file · 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._