Propose a patch

Evidence

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

diff --git a/test/core.test.ts b/test/core.test.ts
--- a/test/core.test.ts
+++ b/test/core.test.ts
@@ -141,1 +141,0 @@
-["credentials in URL", { endpoint: "https://u:[email protected]" }],
diff --git a/test/fixtures/spdl/golden.json b/test/fixtures/spdl/golden.json
--- a/test/fixtures/spdl/golden.json
+++ b/test/fixtures/spdl/golden.json
@@ -9455,1 +9455,0 @@
-"spdl": "grantuser alice read book",
@@ -9469,1 +9468,0 @@
-"spdl": "grant​user alice read book",
@@ -10889,1 +10887,0 @@
-"spdl": "grantgroup employee read,borrow book",
@@ -10903,1 +10900,0 @@
-"spdl": "grant​group employee read,borrow book",
@@ -12043,1 +12039,0 @@
-"spdl": "denyuser bob borrow book if is_card_valid == false",
diff --git a/test/fixtures/spdl/corpus.json b/test/fixtures/spdl/corpus.json
--- a/test/fixtures/spdl/corpus.json
+++ b/test/fixtures/spdl/corpus.json
@@ -1623,1 +1623,0 @@
-"spdl": "grantuser alice read book"
@@ -1627,1 +1626,0 @@
-"spdl": "grant​user alice read book"
@@ -1875,1 +1873,0 @@
-"spdl": "grantgroup employee read,borrow book"
@@ -1879,1 +1876,0 @@
-"spdl": "grant​group employee read,borrow book"
@@ -2083,1 +2079,0 @@
-"spdl": "denyuser bob borrow book if is_card_valid == false"

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: URL with embedded credentials (KillerSkills verdict caution 75)

## 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 75/100**. 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/0.1.0

## Findings with a location
- `test/core.test.ts:141` · URL with embedded credentials — test/core.test.ts:141 · URL with embedded credentials — may be phishing or credential leaking
- `test/fixtures/spdl/golden.json:10889` · Hidden zero-width characters detected — test/fixtures/spdl/golden.json:10889 · Hidden zero-width characters detected — may conceal content
- `test/fixtures/spdl/corpus.json:1875` · Hidden zero-width characters detected — test/fixtures/spdl/corpus.json:1875 · Hidden zero-width characters detected — may conceal content
- `test/fixtures/spdl/corpus.json:2083` · Hidden zero-width characters detected — test/fixtures/spdl/corpus.json:2083 · Hidden zero-width characters detected — may conceal content
- `test/fixtures/spdl/golden.json:9469` · Hidden zero-width characters detected — test/fixtures/spdl/golden.json:9469 · Hidden zero-width characters detected — may conceal content
- `test/fixtures/spdl/corpus.json:1627` · Hidden zero-width characters detected — test/fixtures/spdl/corpus.json:1627 · Hidden zero-width characters detected — may conceal content
- `test/fixtures/spdl/golden.json:12043` · Hidden zero-width characters detected — test/fixtures/spdl/golden.json:12043 · Hidden zero-width characters detected — may conceal content
- `test/fixtures/spdl/corpus.json:1879` · Hidden zero-width characters detected — test/fixtures/spdl/corpus.json:1879 · Hidden zero-width characters detected — may conceal content
- `test/fixtures/spdl/corpus.json:1623` · Hidden zero-width characters detected — test/fixtures/spdl/corpus.json:1623 · Hidden zero-width characters detected — may conceal content
- `test/fixtures/spdl/golden.json:10903` · Hidden zero-width characters detected — test/fixtures/spdl/golden.json:10903 · Hidden zero-width characters detected — may conceal content
- `test/fixtures/spdl/golden.json:9455` · Hidden zero-width characters detected — test/fixtures/spdl/golden.json:9455 · Hidden zero-width characters detected — may conceal content

## Proposed change
The attached patch removes the 11 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._