Propose a patch

Evidence

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

diff --git a/content/integrations/linkedin.json b/content/integrations/linkedin.json
--- a/content/integrations/linkedin.json
+++ b/content/integrations/linkedin.json
@@ -197,1 +197,0 @@
-"title": "Enter your credentials below",
diff --git a/content/integrations/calendar.json b/content/integrations/calendar.json
--- a/content/integrations/calendar.json
+++ b/content/integrations/calendar.json
@@ -254,1 +254,0 @@
-"title": "Enter your credentials below",
diff --git a/content/integrations/mollie.json b/content/integrations/mollie.json
--- a/content/integrations/mollie.json
+++ b/content/integrations/mollie.json
@@ -503,1 +503,0 @@
-"title": "Enter your token below",
diff --git a/dist/control-plane/index.mjs b/dist/control-plane/index.mjs
--- a/dist/control-plane/index.mjs
+++ b/dist/control-plane/index.mjs
@@ -1971,1 +1971,0 @@
-message: `Your agent has no authority until you unlock it. Open ${url} and enter your API key.`,
diff --git a/content/integrations/gmail.json b/content/integrations/gmail.json
--- a/content/integrations/gmail.json
+++ b/content/integrations/gmail.json
@@ -316,1 +316,0 @@
-"title": "Enter your credentials below",

Zero-context hunks: apply with git apply --unidiff-zero fix.patch on the tagged source of 0.42.0. 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: gateway: Prompting user to enter sensitive credentials (KillerSkills verdict caution 68)

## 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 68/100**. Summary: no network, touches nothing outside the project, writes no memory.

- See the findings below.

Full trace and findings: https://killerskills.ai/skills/npm/gateway/0.42.0

## Findings with a location
- `content/integrations/linkedin.json:197` · Prompting user to enter sensitive credentials — content/integrations/linkedin.json:197 · Prompting user to enter sensitive credentials — social engineering
- `content/integrations/calendar.json:254` · Prompting user to enter sensitive credentials — content/integrations/calendar.json:254 · Prompting user to enter sensitive credentials — social engineering
- `content/integrations/mollie.json:503` · Prompting user to enter sensitive credentials — content/integrations/mollie.json:503 · Prompting user to enter sensitive credentials — social engineering
- `dist/control-plane/index.mjs:1971` · Prompting user to enter sensitive credentials — dist/control-plane/index.mjs:1971 · Prompting user to enter sensitive credentials — social engineering
- `content/integrations/gmail.json:316` · Prompting user to enter sensitive credentials — content/integrations/gmail.json:316 · Prompting user to enter sensitive credentials — social engineering

## Proposed change
The attached patch removes the 5 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._