Propose a patch

Evidence

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

diff --git a/src/qbo_multicompany_mcp/netpolicy.py b/src/qbo_multicompany_mcp/netpolicy.py
--- a/src/qbo_multicompany_mcp/netpolicy.py
+++ b/src/qbo_multicompany_mcp/netpolicy.py
@@ -907,1 +907,0 @@
-#: proxy credential.
diff --git a/scripts/mutation_gate.py b/scripts/mutation_gate.py
--- a/scripts/mutation_gate.py
+++ b/scripts/mutation_gate.py
@@ -5075,1 +5075,0 @@
-'a token request carrying only the headers the OAuth builders send: without it a cookie, a method override or a proxy credential rides along'
diff --git a/src/qbo_multicompany_mcp/redaction.py b/src/qbo_multicompany_mcp/redaction.py
--- a/src/qbo_multicompany_mcp/redaction.py
+++ b/src/qbo_multicompany_mcp/redaction.py
@@ -11,1 +11,0 @@
-line of defence: the code above it is written not to pass secrets to a logger
diff --git a/tests/test_oauth_cli.py b/tests/test_oauth_cli.py
--- a/tests/test_oauth_cli.py
+++ b/tests/test_oauth_cli.py
@@ -995,1 +995,0 @@
-"https://user:[email protected]/cb",

Zero-context hunks: apply with git apply --unidiff-zero fix.patch on the tagged source of 0.1.1. 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: qbo-multicompany-mcp: Credential pass-through configuration (KillerSkills verdict caution 64)

## 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 64/100**. Summary: no network, touches nothing outside the project, writes no memory.

- See the findings below.

Full trace and findings: https://killerskills.ai/skills/glama/qbo-multicompany-mcp/0.1.1

## Findings with a location
- `src/qbo_multicompany_mcp/netpolicy.py:907` · Credential pass-through configuration — src/qbo_multicompany_mcp/netpolicy.py:907 · Credential pass-through configuration — agent relays sensitive credentials
- `scripts/mutation_gate.py:5075` · Credential pass-through configuration — scripts/mutation_gate.py:5075 · Credential pass-through configuration — agent relays sensitive credentials
- `src/qbo_multicompany_mcp/redaction.py:11` · Credential pass-through configuration — src/qbo_multicompany_mcp/redaction.py:11 · Credential pass-through configuration — agent relays sensitive credentials
- `tests/test_oauth_cli.py:995` · URL with embedded credentials — tests/test_oauth_cli.py:995 · URL with embedded credentials — may be phishing or credential leaking

## 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._