Propose a patch

Evidence

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

diff --git a/src/http.ts b/src/http.ts
--- a/src/http.ts
+++ b/src/http.ts
@@ -76,1 +76,0 @@
-send(res, 401, "Sign in with your relay token as the password.\n", {
diff --git a/src/secrets.ts b/src/secrets.ts
--- a/src/secrets.ts
+++ b/src/secrets.ts
@@ -12,1 +12,0 @@
-["a relay token", /\bmrt_[A-Za-z0-9_-]{43}/],
diff --git a/test/secrets.test.ts b/test/secrets.test.ts
--- a/test/secrets.test.ts
+++ b/test/secrets.test.ts
@@ -19,1 +19,0 @@
-["relay token", "mr" + "t_" + x(43)],

Zero-context hunks: apply with git apply --unidiff-zero fix.patch on the tagged source of 0.1.0. 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: mcp-relay: Credential pass-through configuration (KillerSkills verdict caution 77)

## What the honeypot observed
KillerSkills ran **[email protected]** in an isolated sandbox (decoy credentials, recording proxy, syscall trace; engine 1.7) and scored it **CAUTION 77/100**. Summary: no network, touches nothing outside the project, writes no memory.

- See the findings below.

Full trace and findings: https://killerskills.ai/skills/glama/mcp-relay/0.1.0

## Findings with a location
- `src/http.ts:76` · Credential pass-through configuration — src/http.ts:76 · Credential pass-through configuration — agent relays sensitive credentials
- `src/secrets.ts:12` · Credential pass-through configuration — src/secrets.ts:12 · Credential pass-through configuration — agent relays sensitive credentials
- `test/secrets.test.ts:19` · Credential pass-through configuration — test/secrets.test.ts:19 · 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._