Propose a patch

Evidence

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

diff --git a/references/onboarding-guide.md b/references/onboarding-guide.md
--- a/references/onboarding-guide.md
+++ b/references/onboarding-guide.md
@@ -1,1 +1,0 @@
-GENERATED FILE: edit shared/shopify-admin-onboarding/core.md or manifest.json, then run node scripts/sync-onboarding.mjs --write.
diff --git a/tests/test-shopify-blog-seo-optimizer.mjs b/tests/test-shopify-blog-seo-optimizer.mjs
--- a/tests/test-shopify-blog-seo-optimizer.mjs
+++ b/tests/test-shopify-blog-seo-optimizer.mjs
@@ -18,1 +18,0 @@
-assert.throws(() => validatePublicUrl("https://user:[email protected]/article"), /Credential-bearing/);
diff --git a/SKILL.md b/SKILL.md
--- a/SKILL.md
+++ b/SKILL.md
@@ -91,1 +91,0 @@
-- `407`: fix proxy credentials in the runtime secret store; never paste them in chat.

Zero-context hunks: apply with git apply --unidiff-zero fix.patch on the tagged source of 1.0.1. 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: shopify-blog-seo-optimizer: HTML comment carrying imperative instructions to the agent (KillerSkills verdict caution 73)

## 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 73/100**. Summary: no network, touches nothing outside the project, writes no memory.

- See the findings below.

Full trace and findings: https://killerskills.ai/skills/clawhub/shopify-blog-seo-optimizer/1.0.1

## Findings with a location
- `references/onboarding-guide.md:1` · HTML comment carrying imperative instructions to the agent — references/onboarding-guide.md:1 · HTML comment carrying imperative instructions to the agent
- `tests/test-shopify-blog-seo-optimizer.mjs:18` · URL with embedded credentials — tests/test-shopify-blog-seo-optimizer.mjs:18 · URL with embedded credentials — may be phishing or credential leaking
- `SKILL.md:91` · Credential pass-through configuration — SKILL.md:91 · Credential pass-through configuration — agent relays sensitive credentials

## 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._