Propose a patch

Evidence

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

diff --git a/tests/test_search_handoff.py b/tests/test_search_handoff.py
--- a/tests/test_search_handoff.py
+++ b/tests/test_search_handoff.py
@@ -61,1 +61,0 @@
-"key sk-ant-api03-abcdefghijklmnopqrstuvwx https://user:pa55w0rd@host/x")
diff --git a/README.md b/README.md
--- a/README.md
+++ b/README.md
@@ -277,1 +277,0 @@
-Tip: add to `CLAUDE.md` / `AGENTS.md`: *"Before asking me about past decisions, search the brain MCP."*

Zero-context hunks: apply with git apply --unidiff-zero fix.patch on the tagged source of 0.4.0. 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: brain: URL with embedded 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/glama/brain/0.4.0

## Findings with a location
- `tests/test_search_handoff.py:61` · URL with embedded credentials — tests/test_search_handoff.py:61 · URL with embedded credentials — may be phishing or credential leaking
- `README.md:277` · Instructs the agent to modify its persistent memory or instruction files — README.md:277 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file · informational: not an instruction file · informational: not an instr

## Proposed change
The attached patch removes the 2 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._