Propose a patch

Evidence

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

diff --git a/scripts/listen.js b/scripts/listen.js
--- a/scripts/listen.js
+++ b/scripts/listen.js
@@ -474,1 +474,0 @@
-message: '👋 Config not found. Paste your API key (mrg_...) to get started.\nCreate your agent at https://mirageclaw.io first.'
diff --git a/SKILL.md b/SKILL.md
--- a/SKILL.md
+++ b/SKILL.md
@@ -34,1 +34,0 @@
-On first connection, an intro message will appear. Paste your API key to begin onboarding. Setup takes about 1 minute.
@@ -85,1 +84,0 @@
-Onboarding starts when you paste your API key for the first time:
@@ -265,1 +263,0 @@
-2. Send `"🔄 Settings reset. Paste your API key (mrg_...) to set up again."`

Zero-context hunks: apply with git apply --unidiff-zero fix.patch on the tagged source of 1.0.13. 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: mirageclaw-marketplace: Prompting user to enter sensitive credentials (KillerSkills verdict blocked 48)

## 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 **BLOCKED 48/100**. Summary: static analysis only — behavior not yet observed.

- See the findings below.

Full trace and findings: https://killerskills.ai/skills/clawhub/mirageclaw-marketplace/1.0.13

## Findings with a location
- `scripts/listen.js:474` · Prompting user to enter sensitive credentials — scripts/listen.js:474 · Prompting user to enter sensitive credentials — social engineering
- `SKILL.md:85` · Prompting user to enter sensitive credentials — SKILL.md:85 · Prompting user to enter sensitive credentials — social engineering
- `SKILL.md:265` · Prompting user to enter sensitive credentials — SKILL.md:265 · Prompting user to enter sensitive credentials — social engineering
- `SKILL.md:34` · Prompting user to enter sensitive credentials — SKILL.md:34 · Prompting user to enter sensitive credentials — social engineering

## 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._