Propose a patch

Evidence

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

diff --git a/.claude/commands/setup.md b/.claude/commands/setup.md
--- a/.claude/commands/setup.md
+++ b/.claude/commands/setup.md
@@ -2,1 +2,0 @@
-description: "Setup omni-ai-mcp: enter your API key in chat to configure everything automatically"
diff --git a/app/core/security.py b/app/core/security.py
--- a/app/core/security.py
+++ b/app/core/security.py
@@ -620,1 +620,0 @@
-# Password in URLs (http://user:pass@host)
diff --git a/CONTRIBUTING.md b/CONTRIBUTING.md
--- a/CONTRIBUTING.md
+++ b/CONTRIBUTING.md
@@ -54,1 +54,0 @@
-5. Update the tool count and tables (README, CLAUDE.md «Available Tools», `tests/integration/test_fastmcp_server.py`) and add a check to `scripts/smoke_live.py`.
diff --git a/README.md b/README.md
--- a/README.md
+++ b/README.md
@@ -292,1 +292,0 @@
-| `/ask-model [model] <prompt>` | Ask any model (GPT, Claude, Llama, Grok, …) |

Zero-context hunks: apply with git apply --unidiff-zero fix.patch on the tagged source of 4.8.2. 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: omni-ai-mcp: 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/pypi/omni-ai-mcp/4.8.2

## Findings with a location
- `.claude/commands/setup.md:2` · Prompting user to enter sensitive credentials — .claude/commands/setup.md:2 · Prompting user to enter sensitive credentials — social engineering
- `app/core/security.py:620` · URL with embedded credentials — app/core/security.py:620 · URL with embedded credentials — may be phishing or credential leaking
- `CONTRIBUTING.md:54` · Instructs the agent to modify its persistent memory or instruction files — CONTRIBUTING.md:54 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file
- `README.md:292` · Fake instruction boundary tag — README.md:292 · Fake instruction boundary tag · informational: not an instruction file

## 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._